Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimo...Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.展开更多
In recent years,the transformer model has demonstrated excellent performance in computer vision(CV)applications.The key lies in its guided representation attention mechanism,which uses dot-product to depict complex fe...In recent years,the transformer model has demonstrated excellent performance in computer vision(CV)applications.The key lies in its guided representation attention mechanism,which uses dot-product to depict complex feature relationships,and comprehensively understands the context semantics to obtain feature weights.Then feature enhancement is implemented by guiding the target matrix through feature weights.However,the uncertainty and inconsistency of features are widespread that prone to confusion in the description of relationships within dot-product attention mechanisms.To solve this problem,this paper proposed a novel approximate-guided representation learning methodology for vision transformer.The kernelised matroids fuzzy rough set is defined,wherein the closed sets inside kernelised fuzzy information granules of matroids structures can constitute the subspace of lower approximation in rough sets.Thus,the kernel relation is employed to characterise image feature granules that will be reconstructed according to the independent set in matroids theory.Then,according to the characteristics of the closed set within matroids,the feature attention weight is formed by using the lower approximation to realise the approximate guidance of features.The approximate-guided representation mechanism can be flexibly deployed as a plug-and-play component in a wide range of CV tasks.Extensive empirical results demonstrate that the proposed method outperforms the majority of advanced prevalent models,especially in terms of robustness.展开更多
Clustering is a pivotal data analysis method for deciphering the charge transport properties of single molecules in break junction experiments.However,given the high dimensionality and variability of the data,feature ...Clustering is a pivotal data analysis method for deciphering the charge transport properties of single molecules in break junction experiments.However,given the high dimensionality and variability of the data,feature extraction remains a bottleneck in the development of efficient clustering methods.In this regard,extensive research over the past two decades has focused on feature engineering and dimensionality reduction in break junction conductance.However,extracting highly relevant features without expert knowledge remains an unresolved challenge.To address this issue,we propose a deep clustering method driven by task-oriented representation learning(CTRL)in which the clustering module serves as a guide for the representation learning(RepL)module.First,we determine an optimal autoencoder(AE)structure through a neural architecture search(NAS)to ensure efficient RepL;second,the RepL process is guided by a joint training strategy that combines AE reconstruction loss with the clustering objective.The results demonstrate that CTRL achieves excellent performance on both the generated and experimental data.Further inspection of the RepL step reveals that joint training robustly learns more compact features than the unconstrained AE or traditional dimensionality reduction methods,significantly reducing misclustering possibilities.Our method provides a general end-to-end automatic clustering solution for analyzing single-molecule break junction data.展开更多
Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the...Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the relatively slow convergence and the need to perform additional,potentially expensive training for new PDE parameters.To solve this limitation,we introduce LatentPINN,a framework that utilizes latent representations of the PDE parameters as additional(to the coordinates)inputs into PINNs and allows for training over the distribution of these parameters.Motivated by the recent progress on generative models,we promote using latent diffusion models to learn compressed latent representations of the distribution of PDE parameters as they act as input parameters for NN functional solutions.We use a two-stage training scheme in which,in the first stage,we learn the latent representations for the distribution of PDE parameters.In the second stage,we train a physics-informed neural network over inputs given by randomly drawn samples from the coordinate space within the solution domain and samples from the learned latent representation of the PDE parameters.Considering their importance in capturing evolving interfaces and fronts in various fields,we test the approach on a class of level set equations given,for example,by the nonlinear Eikonal equation.We share results corresponding to three Eikonal parameters(velocity models)sets.The proposed method performs well on new phase velocity models without the need for any additional training.展开更多
Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insigh...Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.展开更多
Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning dis...Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.展开更多
The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning technique...The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks （CNNs）, part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.展开更多
Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all cha...Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all characteristics of networks.In fact,network vertices usually contain rich text information,which can be well utilized to learn text-enhanced network representations.Meanwhile,Matrix-Forest Index(MFI)has shown its high effectiveness and stability in link prediction tasks compared with other algorithms of link prediction.Both MFI and Inductive Matrix Completion(IMC)are not well applied with algorithmic frameworks of typical representation learning methods.Therefore,we proposed a novel semi-supervised algorithm,tri-party deep network representation learning using inductive matrix completion(TDNR).Based on inductive matrix completion algorithm,TDNR incorporates text features,the link certainty degrees of existing edges and the future link probabilities of non-existing edges into network representations.The experimental results demonstrated that TFNR outperforms other baselines on three real-world datasets.The visualizations of TDNR show that proposed algorithm is more discriminative than other unsupervised approaches.展开更多
Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning th...Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability.Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.展开更多
Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artif...Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.展开更多
In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owin...In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owing to the lack of accurately labeled network traffic data,many unsupervised feature representation learning models have been proposed with state-of-theart performance.Yet,these models fail to consider the classification error while learning the feature representation.Intuitively,the learnt feature representation may degrade the performance of the classification task.For the first time in the field of intrusion detection,this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder(DAE)for learning the robust feature representation and one-class support vector machine(OCSVM)for finding the more compact decision hyperplane for intrusion detection.Specially,the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously.This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection.Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model.First,the ablation evaluation on benchmark dataset,NSL-KDD validates the design decision of the proposed model.Next,the performance evaluation on recent intrusion dataset,UNSW-NB15 signifies the stable performance of the proposed model.Finally,the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.展开更多
Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs ...Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.展开更多
Fine-grained weather forecasting data,i.e.,the grid data with high-resolution,have attracted increasing attention in recent years,especially for some specific applications such as the Winter Olympic Games.Although Eur...Fine-grained weather forecasting data,i.e.,the grid data with high-resolution,have attracted increasing attention in recent years,especially for some specific applications such as the Winter Olympic Games.Although European Centre for Medium-Range Weather Forecasts(ECMWF)provides grid prediction up to 240 hours,the coarse data are unable to meet high requirements of these major events.In this paper,we propose a method,called model residual machine learning(MRML),to generate grid prediction with high-resolution based on high-precision stations forecasting.MRML applies model output machine learning(MOML)for stations forecasting.Subsequently,MRML utilizes these forecasts to improve the quality of the grid data by fitting a machine learning(ML)model to the residuals.We demonstrate that MRML achieves high capability at diverse meteorological elements,specifically,temperature,relative humidity,and wind speed.In addition,MRML could be easily extended to other post-processing methods by invoking different techniques.In our experiments,MRML outperforms the traditional downscaling methods such as piecewise linear interpolation(PLI)on the testing data.展开更多
Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appea...Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appear at the initial level. To preventblindness, early detection and regular treatment are needed. Automated detectionbased on machine intelligence may assist the ophthalmologist in examining thepatients’ condition more accurately and efficiently. The purpose of this study is toproduce an automated screening system for recognition and grading of diabetic retinopathyusing machine learning through deep transfer and representational learning.The artificial intelligence technique used is transfer learning on the deep neural network,Inception-v4. Two configuration variants of transfer learning are applied onInception-v4: Fine-tune mode and fixed feature extractor mode. Both configurationmodes have achieved decent accuracy values, but the fine-tuning method outperformsthe fixed feature extractor configuration mode. Fine-tune configuration modehas gained 96.6% accuracy in early detection of DR and 97.7% accuracy in gradingthe disease and has outperformed the state of the art methods in the relevant literature.展开更多
Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fin...Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.展开更多
Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scal...Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.展开更多
The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system f...The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system from the perspective of route network analysis,and the attribute information of airport nodes in the airport route network is not appropriately integrated into the airport network.In order to solve this problem,a multi-airport system homogeneity analysis method based on airport attribute network representation learning is proposed.Firstly,the route network of a multi-airport system with attribute information is constructed.If there are flights between airports,an edge is added between airports,and regional attribute information is added for each airport node.Secondly,the airport attributes and the airport network vector are represented respectively.The airport attributes and the airport network vector are embedded into the unified airport representation vector space by the network representation learning method,and then the airport vector integrating the airport attributes and the airport network characteristics is obtained.By calculating the similarity of the airport vectors,it is convenient to calculate the degree of homogeneity between airports and the homogeneity of the multi-airport system.The experimental results on the Beijing-Tianjin-Hebei multi-airport system show that,compared with other existing algorithms,the homogeneity analysis method based on attributed network representation learning can get more consistent results with the current situation of Beijing-Tianjin-Hebei multi-airport system.展开更多
Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representation...Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representations.However,due to limitations in code representation and neural network design,the validity and practicality of the model still need to be improved.Additionally,due to differences in programming languages,most methods lack cross-language detection generality.To address these issues,in this paper,we analyze the shortcomings of previous code representations and neural networks.We propose a novel hierarchical code representation that combines Concrete Syntax Trees(CST)with Program Dependence Graphs(PDG).Furthermore,we introduce a Tree-Graph-Gated-Attention(TGGA)network based on gated recurrent units and attention mechanisms to build a Hierarchical Code Representation learning-based Vulnerability Detection(HCRVD)system.This system enables cross-language vulnerability detection at the function-level.The experiments show that HCRVD surpasses many competitors in vulnerability detection capabilities.It benefits from the hierarchical code representation learning method,and outperforms baseline in cross-language vulnerability detection by 9.772%and 11.819%in the C/C++and Java datasets,respectively.Moreover,HCRVD has certain ability to detect vulnerabilities in unknown programming languages and is useful in real open-source projects.HCRVD shows good validity,generality and practicality.展开更多
A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chin...A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semanties of loeal context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the eharaeter representations as its input features. Finally, experimental results show that Chinese charaeter representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure.展开更多
A method of knowledge representation and learning based on fuzzy Petri nets was designed. In this way the parameters of weights, threshold value and certainty factor in knowledge model can be adjusted dynamically. The...A method of knowledge representation and learning based on fuzzy Petri nets was designed. In this way the parameters of weights, threshold value and certainty factor in knowledge model can be adjusted dynamically. The advantages of knowledge representation based on production rules and neural networks were integrated into this method. Just as production knowledge representation, this method has clear structure and specific parameters meaning. In addition, it has learning and parallel reasoning ability as neural networks knowledge representation does. The result of simulation shows that the learning algorithm can converge, and the parameters of weights, threshold value and certainty factor can reach the ideal level after training.展开更多
基金supported by the Science and Technology Project of Henan Province(No.222102210081).
文摘Joint Multimodal Aspect-based Sentiment Analysis(JMASA)is a significant task in the research of multimodal fine-grained sentiment analysis,which combines two subtasks:Multimodal Aspect Term Extraction(MATE)and Multimodal Aspect-oriented Sentiment Classification(MASC).Currently,most existing models for JMASA only perform text and image feature encoding from a basic level,but often neglect the in-depth analysis of unimodal intrinsic features,which may lead to the low accuracy of aspect term extraction and the poor ability of sentiment prediction due to the insufficient learning of intra-modal features.Given this problem,we propose a Text-Image Feature Fine-grained Learning(TIFFL)model for JMASA.First,we construct an enhanced adjacency matrix of word dependencies and adopt graph convolutional network to learn the syntactic structure features for text,which addresses the context interference problem of identifying different aspect terms.Then,the adjective-noun pairs extracted from image are introduced to enable the semantic representation of visual features more intuitive,which addresses the ambiguous semantic extraction problem during image feature learning.Thereby,the model performance of aspect term extraction and sentiment polarity prediction can be further optimized and enhanced.Experiments on two Twitter benchmark datasets demonstrate that TIFFL achieves competitive results for JMASA,MATE and MASC,thus validating the effectiveness of our proposed methods.
基金supported in part by the National Natural Science Foundation of China(62471205,62462040)Yunnan Fundamental Research Projects(202301AV070003)+1 种基金Major Science and Technology Projects in Yunnan Province(202302AG050009,202202AD080013)Sichuan Provincial Key Laboratory of Philosophy and Social Science for Language Intelligence in Special Education Major Project(YYZN-2024-1).
文摘In recent years,the transformer model has demonstrated excellent performance in computer vision(CV)applications.The key lies in its guided representation attention mechanism,which uses dot-product to depict complex feature relationships,and comprehensively understands the context semantics to obtain feature weights.Then feature enhancement is implemented by guiding the target matrix through feature weights.However,the uncertainty and inconsistency of features are widespread that prone to confusion in the description of relationships within dot-product attention mechanisms.To solve this problem,this paper proposed a novel approximate-guided representation learning methodology for vision transformer.The kernelised matroids fuzzy rough set is defined,wherein the closed sets inside kernelised fuzzy information granules of matroids structures can constitute the subspace of lower approximation in rough sets.Thus,the kernel relation is employed to characterise image feature granules that will be reconstructed according to the independent set in matroids theory.Then,according to the characteristics of the closed set within matroids,the feature attention weight is formed by using the lower approximation to realise the approximate guidance of features.The approximate-guided representation mechanism can be flexibly deployed as a plug-and-play component in a wide range of CV tasks.Extensive empirical results demonstrate that the proposed method outperforms the majority of advanced prevalent models,especially in terms of robustness.
基金supported by Guangxi Science and Technology Program(No.GuiKeAD23026291)Guangxi Science and Technology Major Project(No.AA22068057).
文摘Clustering is a pivotal data analysis method for deciphering the charge transport properties of single molecules in break junction experiments.However,given the high dimensionality and variability of the data,feature extraction remains a bottleneck in the development of efficient clustering methods.In this regard,extensive research over the past two decades has focused on feature engineering and dimensionality reduction in break junction conductance.However,extracting highly relevant features without expert knowledge remains an unresolved challenge.To address this issue,we propose a deep clustering method driven by task-oriented representation learning(CTRL)in which the clustering module serves as a guide for the representation learning(RepL)module.First,we determine an optimal autoencoder(AE)structure through a neural architecture search(NAS)to ensure efficient RepL;second,the RepL process is guided by a joint training strategy that combines AE reconstruction loss with the clustering objective.The results demonstrate that CTRL achieves excellent performance on both the generated and experimental data.Further inspection of the RepL step reveals that joint training robustly learns more compact features than the unconstrained AE or traditional dimensionality reduction methods,significantly reducing misclustering possibilities.Our method provides a general end-to-end automatic clustering solution for analyzing single-molecule break junction data.
基金King Abdullah University of Science and Technol-ogy(KAUST)for supporting this research and the Seismic Wave Anal-ysis group for the supportive and encouraging environment.
文摘Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the relatively slow convergence and the need to perform additional,potentially expensive training for new PDE parameters.To solve this limitation,we introduce LatentPINN,a framework that utilizes latent representations of the PDE parameters as additional(to the coordinates)inputs into PINNs and allows for training over the distribution of these parameters.Motivated by the recent progress on generative models,we promote using latent diffusion models to learn compressed latent representations of the distribution of PDE parameters as they act as input parameters for NN functional solutions.We use a two-stage training scheme in which,in the first stage,we learn the latent representations for the distribution of PDE parameters.In the second stage,we train a physics-informed neural network over inputs given by randomly drawn samples from the coordinate space within the solution domain and samples from the learned latent representation of the PDE parameters.Considering their importance in capturing evolving interfaces and fronts in various fields,we test the approach on a class of level set equations given,for example,by the nonlinear Eikonal equation.We share results corresponding to three Eikonal parameters(velocity models)sets.The proposed method performs well on new phase velocity models without the need for any additional training.
基金supported by the Natural Science Foundation of Wenzhou University of Technology,China(Grant No.:ky202211).
文摘Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.
基金supported by National Basic Research Program of China (973 Program) (No. 2015CB352502)National Nature Science Foundation of China (No. 61573026)Beijing Nature Science Foundation (No. L172037)
文摘Fine-grained image classification, which aims to distinguish images with subtle distinctions, is a challenging task for two main reasons: lack of sufficient training data for every class and difficulty in learning discriminative features for representation. In this paper, to address the two issues, we propose a two-phase framework for recognizing images from unseen fine-grained classes, i.e., zeroshot fine-grained classification. In the first feature learning phase, we finetune deep convolutional neural networks using hierarchical semantic structure among fine-grained classes to extract discriminative deep visual features. Meanwhile, a domain adaptation structure is induced into deep convolutional neural networks to avoid domain shift from training data to test data. In the second label inference phase, a semantic directed graph is constructed over attributes of fine-grained classes. Based on this graph, we develop a label propagation algorithm to infer the labels of images in the unseen classes. Experimental results on two benchmark datasets demonstrate that our model outperforms the state-of-the-art zero-shot learning models. In addition, the features obtained by our feature learning model also yield significant gains when they are used by other zero-shot learning models, which shows the flexility of our model in zero-shot finegrained classification.
基金supported by the National Natural Science Foundation of China(Nos.61373121 and 61328205)Program for Sichuan Provincial Science Fund for Distinguished Young Scholars(No.13QNJJ0149)+1 种基金the Fundamental Research Funds for the Central UniversitiesChina Scholarship Council(No.201507000032)
文摘The deep learning technology has shown impressive performance in various vision tasks such as image classification, object detection and semantic segmentation. In particular, recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories, such as bird species or dog breeds. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we review four types of deep learning based fine-grained image classification approaches, including the general convolutional neural networks （CNNs）, part detection based, ensemble of networks based and visual attention based fine-grained image classification approaches. Besides, the deep learning based semantic segmentation approaches are also covered in this paper. The region proposal based and fully convolutional networks based approaches for semantic segmentation are introduced respectively.
基金Projects(11661069,61763041) supported by the National Natural Science Foundation of ChinaProject(IRT_15R40) supported by Changjiang Scholars and Innovative Research Team in University,ChinaProject(2017TS045) supported by the Fundamental Research Funds for the Central Universities,China
文摘Most existing network representation learning algorithms focus on network structures for learning.However,network structure is only one kind of view and feature for various networks,and it cannot fully reflect all characteristics of networks.In fact,network vertices usually contain rich text information,which can be well utilized to learn text-enhanced network representations.Meanwhile,Matrix-Forest Index(MFI)has shown its high effectiveness and stability in link prediction tasks compared with other algorithms of link prediction.Both MFI and Inductive Matrix Completion(IMC)are not well applied with algorithmic frameworks of typical representation learning methods.Therefore,we proposed a novel semi-supervised algorithm,tri-party deep network representation learning using inductive matrix completion(TDNR).Based on inductive matrix completion algorithm,TDNR incorporates text features,the link certainty degrees of existing edges and the future link probabilities of non-existing edges into network representations.The experimental results demonstrated that TFNR outperforms other baselines on three real-world datasets.The visualizations of TDNR show that proposed algorithm is more discriminative than other unsupervised approaches.
基金by National Natural Science Foundation of China(Nos.61822204 and 61521002).
文摘Learning discriminative representations with deep neural networks often relies on massive labeled data, which is expensive and difficult to obtain in many real scenarios. As an alternative, self-supervised learning that leverages input itself as supervision is strongly preferred for its soaring performance on visual representation learning. This paper introduces a contrastive self-supervised framework for learning generalizable representations on the synthetic data that can be obtained easily with complete controllability.Specifically, we propose to optimize a contrastive learning task and a physical property prediction task simultaneously. Given the synthetic scene, the first task aims to maximize agreement between a pair of synthetic images generated by our proposed view sampling module, while the second task aims to predict three physical property maps, i.e., depth, instance contour maps, and surface normal maps. In addition, a feature-level domain adaptation technique with adversarial training is applied to reduce the domain difference between the realistic and the synthetic data. Experiments demonstrate that our proposed method achieves state-of-the-art performance on several visual recognition datasets.
文摘Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.
基金This work was supported by the Research Deanship of Prince Sattam Bin Abdulaziz University,Al-Kharj,Saudi Arabia(Grant No.2020/01/17215).Also,the author thanks Deanship of college of computer engineering and sciences for technical support provided to complete the project successfully。
文摘In the era of Big data,learning discriminant feature representation from network traffic is identified has as an invariably essential task for improving the detection ability of an intrusion detection system(IDS).Owing to the lack of accurately labeled network traffic data,many unsupervised feature representation learning models have been proposed with state-of-theart performance.Yet,these models fail to consider the classification error while learning the feature representation.Intuitively,the learnt feature representation may degrade the performance of the classification task.For the first time in the field of intrusion detection,this paper proposes an unsupervised IDS model leveraging the benefits of deep autoencoder(DAE)for learning the robust feature representation and one-class support vector machine(OCSVM)for finding the more compact decision hyperplane for intrusion detection.Specially,the proposed model defines a new unified objective function to minimize the reconstruction and classification error simultaneously.This unique contribution not only enables the model to support joint learning for feature representation and classifier training but also guides to learn the robust feature representation which can improve the discrimination ability of the classifier for intrusion detection.Three set of evaluation experiments are conducted to demonstrate the potential of the proposed model.First,the ablation evaluation on benchmark dataset,NSL-KDD validates the design decision of the proposed model.Next,the performance evaluation on recent intrusion dataset,UNSW-NB15 signifies the stable performance of the proposed model.Finally,the comparative evaluation verifies the efficacy of the proposed model against recently published state-of-the-art methods.
基金This work was supported by National Natural Science Foundation of China(NSFC)under Grant No.61771299,No.61771322,No.61375015,No.61301027.
文摘Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.
基金Project supported by the National Natural Science Foundation of China(Nos.12101072 and 11421101)the National Key Research and Development Program of China(No.2018YFF0300104)+1 种基金the Beijing Municipal Science and Technology Project(No.Z201100005820002)the Open Research Fund of Shenzhen Research Institute of Big Data(No.2019ORF01001)。
文摘Fine-grained weather forecasting data,i.e.,the grid data with high-resolution,have attracted increasing attention in recent years,especially for some specific applications such as the Winter Olympic Games.Although European Centre for Medium-Range Weather Forecasts(ECMWF)provides grid prediction up to 240 hours,the coarse data are unable to meet high requirements of these major events.In this paper,we propose a method,called model residual machine learning(MRML),to generate grid prediction with high-resolution based on high-precision stations forecasting.MRML applies model output machine learning(MOML)for stations forecasting.Subsequently,MRML utilizes these forecasts to improve the quality of the grid data by fitting a machine learning(ML)model to the residuals.We demonstrate that MRML achieves high capability at diverse meteorological elements,specifically,temperature,relative humidity,and wind speed.In addition,MRML could be easily extended to other post-processing methods by invoking different techniques.In our experiments,MRML outperforms the traditional downscaling methods such as piecewise linear interpolation(PLI)on the testing data.
基金the National Research Foundation(NRF)of Korea under the auspices of the Ministry of Science and ICT,Republic of Korea(Grant No.NRF-2020R1G1A1012741)received by M.R.Bhutta.https://nrf.kird.re.kr/main.do.
文摘Diabetic retinopathy (DR) is a retinal disease that causes irreversible blindness.DR occurs due to the high blood sugar level of the patient, and it is clumsy tobe detected at an early stage as no early symptoms appear at the initial level. To preventblindness, early detection and regular treatment are needed. Automated detectionbased on machine intelligence may assist the ophthalmologist in examining thepatients’ condition more accurately and efficiently. The purpose of this study is toproduce an automated screening system for recognition and grading of diabetic retinopathyusing machine learning through deep transfer and representational learning.The artificial intelligence technique used is transfer learning on the deep neural network,Inception-v4. Two configuration variants of transfer learning are applied onInception-v4: Fine-tune mode and fixed feature extractor mode. Both configurationmodes have achieved decent accuracy values, but the fine-tuning method outperformsthe fixed feature extractor configuration mode. Fine-tune configuration modehas gained 96.6% accuracy in early detection of DR and 97.7% accuracy in gradingthe disease and has outperformed the state of the art methods in the relevant literature.
文摘Fine-grained image search is one of the most challenging tasks in computer vision that aims to retrieve similar images at the fine-grained level for a given query image.The key objective is to learn discriminative fine-grained features by training deep models such that similar images are clustered,and dissimilar images are separated in the low embedding space.Previous works primarily focused on defining local structure loss functions like triplet loss,pairwise loss,etc.However,training via these approaches takes a long training time,and they have poor accuracy.Additionally,representations learned through it tend to tighten up in the embedded space and lose generalizability to unseen classes.This paper proposes a noise-assisted representation learning method for fine-grained image retrieval to mitigate these issues.In the proposed work,class manifold learning is performed in which positive pairs are created with noise insertion operation instead of tightening class clusters.And other instances are treated as negatives within the same cluster.Then a loss function is defined to penalize when the distance between instances of the same class becomes too small relative to the noise pair in that class in embedded space.The proposed approach is validated on CARS-196 and CUB-200 datasets and achieved better retrieval results(85.38%recall@1 for CARS-196%and 70.13%recall@1 for CUB-200)compared to other existing methods.
基金This research was funded by King Mongkut’s University of Technology North Bangkok(Contract no.KMUTNB-62-KNOW-026).
文摘Fine-grained image classification is a challenging research topic because of the high degree of similarity among categories and the high degree of dissimilarity for a specific category caused by different poses and scales.A cul-tural heritage image is one of thefine-grained images because each image has the same similarity in most cases.Using the classification technique,distinguishing cultural heritage architecture may be difficult.This study proposes a cultural heri-tage content retrieval method using adaptive deep learning forfine-grained image retrieval.The key contribution of this research was the creation of a retrieval mod-el that could handle incremental streams of new categories while maintaining its past performance in old categories and not losing the old categorization of a cul-tural heritage image.The goal of the proposed method is to perform a retrieval task for classes.Incremental learning for new classes was conducted to reduce the re-training process.In this step,the original class is not necessary for re-train-ing which we call an adaptive deep learning technique.Cultural heritage in the case of Thai archaeological site architecture was retrieved through machine learn-ing and image processing.We analyze the experimental results of incremental learning forfine-grained images with images of Thai archaeological site architec-ture from world heritage provinces in Thailand,which have a similar architecture.Using afine-grained image retrieval technique for this group of cultural heritage images in a database can solve the problem of a high degree of similarity among categories and a high degree of dissimilarity for a specific category.The proposed method for retrieving the correct image from a database can deliver an average accuracy of 85 percent.Adaptive deep learning forfine-grained image retrieval was used to retrieve cultural heritage content,and it outperformed state-of-the-art methods infine-grained image retrieval.
基金supported by the Natural Science Foundation of Tianjin(No.20JCQNJC00720)the Fundamental Research Fund for the Central Universities(No.3122021052)。
文摘The homogeneity analysis of multi-airport system can provide important decision-making support for the route layout and cooperative operation.Existing research seldom analyzes the homogeneity of multi-airport system from the perspective of route network analysis,and the attribute information of airport nodes in the airport route network is not appropriately integrated into the airport network.In order to solve this problem,a multi-airport system homogeneity analysis method based on airport attribute network representation learning is proposed.Firstly,the route network of a multi-airport system with attribute information is constructed.If there are flights between airports,an edge is added between airports,and regional attribute information is added for each airport node.Secondly,the airport attributes and the airport network vector are represented respectively.The airport attributes and the airport network vector are embedded into the unified airport representation vector space by the network representation learning method,and then the airport vector integrating the airport attributes and the airport network characteristics is obtained.By calculating the similarity of the airport vectors,it is convenient to calculate the degree of homogeneity between airports and the homogeneity of the multi-airport system.The experimental results on the Beijing-Tianjin-Hebei multi-airport system show that,compared with other existing algorithms,the homogeneity analysis method based on attributed network representation learning can get more consistent results with the current situation of Beijing-Tianjin-Hebei multi-airport system.
基金funded by the Major Science and Technology Projects in Henan Province,China,Grant No.221100210600.
文摘Prior studies have demonstrated that deep learning-based approaches can enhance the performance of source code vulnerability detection by training neural networks to learn vulnerability patterns in code representations.However,due to limitations in code representation and neural network design,the validity and practicality of the model still need to be improved.Additionally,due to differences in programming languages,most methods lack cross-language detection generality.To address these issues,in this paper,we analyze the shortcomings of previous code representations and neural networks.We propose a novel hierarchical code representation that combines Concrete Syntax Trees(CST)with Program Dependence Graphs(PDG).Furthermore,we introduce a Tree-Graph-Gated-Attention(TGGA)network based on gated recurrent units and attention mechanisms to build a Hierarchical Code Representation learning-based Vulnerability Detection(HCRVD)system.This system enables cross-language vulnerability detection at the function-level.The experiments show that HCRVD surpasses many competitors in vulnerability detection capabilities.It benefits from the hierarchical code representation learning method,and outperforms baseline in cross-language vulnerability detection by 9.772%and 11.819%in the C/C++and Java datasets,respectively.Moreover,HCRVD has certain ability to detect vulnerabilities in unknown programming languages and is useful in real open-source projects.HCRVD shows good validity,generality and practicality.
基金Supported by the National Natural Science Foundation of China(No.61303179,U1135005,61175020)
文摘A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semanties of loeal context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the eharaeter representations as its input features. Finally, experimental results show that Chinese charaeter representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure.
文摘A method of knowledge representation and learning based on fuzzy Petri nets was designed. In this way the parameters of weights, threshold value and certainty factor in knowledge model can be adjusted dynamically. The advantages of knowledge representation based on production rules and neural networks were integrated into this method. Just as production knowledge representation, this method has clear structure and specific parameters meaning. In addition, it has learning and parallel reasoning ability as neural networks knowledge representation does. The result of simulation shows that the learning algorithm can converge, and the parameters of weights, threshold value and certainty factor can reach the ideal level after training.
