Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion...Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.展开更多
The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods...The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource demands.Automated Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification tasks.This paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these limitations.Our method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature groups.The Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization problem.Empirical validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.展开更多
In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic op...In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic operating conditions increase the risk of fatigue damage in CNC machine tool bearings,highlighting the urgent demand for rapid and accurate fault diagnosis methods that can maintain production efficiency and extend equipment uptime.However,varying conditions induce feature distribution shifts,and scarce fault samples limitmodel generalization.Therefore,this paper proposes a causal-Transformer-based meta-learning(CTML)method for bearing fault diagnosis in CNC machine tools,comprising three core modules:(1)the original bearing signal is transformed into a multi-scale time-frequency feature space using continuous wavelet transform;(2)a causal-Transformer architecture is designed to achieve feature extraction and fault classification based on the physical causal law of fault propagation;(3)the above mechanisms are integrated into a model-agnostic meta-learning(MAML)framework to achieve rapid cross-condition adaptation through an adaptive gradient pruning strategy.Experimental results using the multiple bearing dataset show that under few-shot cross-condition scenarios(3-way 1-shot and 3-way 5-shot),the proposed CTML outperforms benchmark models(e.g.,Transformer,domain adversarial neural networks(DANN),and MAML)in terms of classification accuracy and sensitivity to operating conditions,while maintaining a moderate level of model complexity.展开更多
Many important problems in science and engineering require solving the so-called parametric partial differential equations(PDEs),i.e.,PDEs with different physical parameters,boundary conditions,shapes of computational...Many important problems in science and engineering require solving the so-called parametric partial differential equations(PDEs),i.e.,PDEs with different physical parameters,boundary conditions,shapes of computational domains,etc.Typical reduced order modeling techniques accelerate the solution of the parametric PDEs by projecting them onto a linear trial manifold constructed in the ofline stage.These methods often need a predefined mesh as well as a series of precomputed solution snapshots,and may struggle to balance between the efficiency and accuracy due to the limitation of the linear ansatz.Utilizing the nonlinear representation of neural networks(NNs),we propose the Meta-Auto-Decoder(MAD)to construct a nonlinear trial manifold,whose best possible performance is measured theoretically by the decoder width.Based on the meta-learning concept,the trial manifold can be learned in a mesh-free and unsupervised way during the pre-training stage.Fast adaptation to new(possibly heterogeneous)PDE parameters is enabled by searching on this trial manifold,and optionally fine-tuning the trial manifold at the same time.Extensive numerical experiments show that the MAD method exhibits a faster convergence speed without losing the accuracy than other deep learning-based methods.展开更多
Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input.Instead of just memorizing a task,this is accomplished through teachi...Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input.Instead of just memorizing a task,this is accomplished through teaching a model how to learn.Algorithms for meta-learning are typically trained on a collection of training problems,each of which has a limited number of labelled instances.Multiple Xray classification tasks,including the detection of pneumonia,coronavirus disease 2019,and other disorders,have demonstrated the effectiveness of meta-learning.Meta-learning has the benefit of allowing models to be trained on dental X-ray datasets that are too few for more conventional machine learning methods.Due to the high cost and lengthy collection process associated with dental imaging datasets,this is significant for dental X-ray classification jobs.The ability to train models that are more resistant to fresh input is another benefit of meta-learning.展开更多
The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep le...The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.展开更多
Currently,one of the most severe problems in the agricultural industry is the effect of diseases and pests on global crop production and economic development.Therefore,further research in the field of crop disease and...Currently,one of the most severe problems in the agricultural industry is the effect of diseases and pests on global crop production and economic development.Therefore,further research in the field of crop disease and pest detection is necessary to address the mentioned problem.Aiming to identify the diseased crops and insect pests timely and accurately and perform appropriate prevention measures to reduce the associated losses,this article proposes a Model-Agnostic Meta-Learning(MAML)attention model based on the meta-learning paradigm.The proposed model combines meta-learning with basic learning and adopts an Efficient Channel Attention(ECA)mod-ule.The module follows the local cross-channel interactive strategy of non-dimensional reduction to strengthen the weight parameters corresponding to certain disease characteristics.The proposed meta-learning-based algorithm has the advantage of strong generalization capability and,by integrating the ECA module in the original model,can achieve more efficient detection in new tasks.The proposed model is verified by experiments,and the experimental results show that compared with the original MAML model,the proposed improved MAML-Attention model has a better performance by 1.8–9.31 percentage points in different classification tasks;the maximum accuracy is increased by 1.15–8.2 percentage points.The experimental results verify the strong generalization ability and good robustness of the proposed MAML-Attention model.Compared to the other few-shot methods,the proposed MAML-Attention performs better.展开更多
In recent years,machine learning has made great progress in intrusion detection,network protection,anomaly detection,and other issues in cyberspace.However,these traditional machine learning algorithms usually require...In recent years,machine learning has made great progress in intrusion detection,network protection,anomaly detection,and other issues in cyberspace.However,these traditional machine learning algorithms usually require a lot of data to learn and have a low recognition rate for unknown attacks.Among them,“one-shot learning”,“few-shot learning”,and“zero-shot learning”are challenges that cannot be ignored for traditional machine learning.The more intractable problem in cyberspace security is the changeable attack mode.When a new attack mode appears,there are few or even zero samples that can be learned.Meta-learning comes from imitating human problem-solving methods as humans can quickly learn unknown things based on their existing knowledge when learning.Its purpose is to quickly obtain a model with high accuracy and strong generalization through less data training.This article first divides the meta-learning model into five research directions based on different principles of use.They are model-based,metric-based,optimization-based,online-learning-based,or stacked ensemble-based.Then,the current problems in the field of cyberspace security are categorized into three branches:cyber security,information security,and artificial intelligence security according to different perspectives.Then,the application research results of various meta-learning models on these three branches are reviewed.At the same time,based on the characteristics of strong generalization,evolution,and scalability of meta-learning,we contrast and summarize its advantages in solving problems.Finally,the prospect of future deep application of meta-learning in the field of cyberspace security is summarized.展开更多
capacity and creativity tendencies among Chinese baccalaureate nursing students.Design:Cross-sectional study design.Methods:A convenient sample of 445 baccalaureate nursing students were surveyed in two universities i...capacity and creativity tendencies among Chinese baccalaureate nursing students.Design:Cross-sectional study design.Methods:A convenient sample of 445 baccalaureate nursing students were surveyed in two universities in Tianjin,China.Students completed a questionnaire that included their demographic information,Achievement Motivation Scale,Meta-Learning Capacity Questionnaire,and Creativity Tendencies Scale.Pearson correlation was performed to test the correlation among achievement motivation,meta-learning capacity and creativity tendencies.Hierarchical linear regression analyses were performed to explore the mediating role of meta-learning capacity.Results:The participants had moderate levels of achievement motivation(mean score 2.383±0.240)and meta-learning capacity(mean score 1.505±0.241)and a medium-high level of creativity tendency(mean score 1.841±0.288).Creativity tendencies was significantly associated with both achievement motivation and meta-learning capacity(both P<0.01).Furthermore,meta-learning capacity mediated the relationship between achievement motivation and high creativity tendencies.Conclusion:The study hypotheses were supported.Higher achievement motivation,and meta-learning capacity can increase creativity tendencies of baccalaureate nursing students,and meta-learning capacity was found to mediate the relationship between achievement motivation and creativity tendencies.Nursing educators should pay attention to the positive role of meta-learning capacity in nursing students’learning,and make them more confident when they finish their studies.展开更多
Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,data distribution of the training set fails to be consistent with the one of the testing set as the limited domain d...Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,data distribution of the training set fails to be consistent with the one of the testing set as the limited domain differences among them.These factors often result in poor generalization in existing meta-learning models.In this work,a novel smoother manifold for graph meta-learning(SGML)is proposed,which derives the similarity parameters of node features from the relationship between nodes and edges in the graph structure,and then utilizes the similarity parameters to yield smoother manifold through embedded propagation module.Smoother manifold can naturally filter out noise from the most important components when generalizing the local mapping relationship to the global.Besides suiting for generalizing on unseen low data issues,the framework is capable to easily perform transductive inference.Experimental results on MiniImageNet and TieredImageNet consistently show that applying SGML to supervised and semi-supervised classification can improve the performance in reducing the noise of domain shift representation.展开更多
Meta-learning algorithms learn about the learning process itself so it can speed up subsequent similar learning tasks with fewer data and iterations. If achieved, these benefits expand the flexibility of traditional m...Meta-learning algorithms learn about the learning process itself so it can speed up subsequent similar learning tasks with fewer data and iterations. If achieved, these benefits expand the flexibility of traditional machine learning to areas where there are small windows of time or data available. One such area is stock trading, where the relevance of data decreases as time passes, requiring fast results on fewer data points to respond to fast-changing market trends. We, to the best of our knowledge, are the first to apply meta-learning algorithms to an evolutionary strategy for stock trading to decrease learning time by using fewer iterations and to achieve higher trading profits with fewer data points. We found that our meta-learning approach to stock trading earns profits similar to a purely evolutionary algorithm. However, it only requires 50 iterations during test, versus thousands that are typically required without meta-learning, or 50% of the training data during test.展开更多
The aviation industry has seen significant advancements in safety procedures over the past few decades, resulting in a steady decline in aviation deaths worldwide. However, the safety standards in General Aviation (GA...The aviation industry has seen significant advancements in safety procedures over the past few decades, resulting in a steady decline in aviation deaths worldwide. However, the safety standards in General Aviation (GA) are still lower compared to those in commercial aviation. With the anticipated growth in air travel, there is an imminent need to improve operational safety in GA. One way to improve aircraft and operational safety is through trajectory prediction. Trajectory prediction plays a key role in optimizing air traffic control and improving overall flight safety. This paper proposes a meta-learning approach to predict short- to mid-term trajectories of aircraft using historical real flight data collected from multiple GA aircraft. The proposed solution brings together multiple models to improve prediction accuracy. In this paper, we are combining two models, Random Forest Regression (RFR) and Long Short-term Memory (LSTM), using k-Nearest Neighbors (k-NN), to output the final prediction based on the combined output of the individual models. This approach gives our model an edge over single-model predictions. We present the results of our meta-learner and evaluate its performance against individual models using the Mean Absolute Error (MAE), Absolute Altitude Error (AAE), and Root Mean Squared Error (RMSE) evaluation metrics. The proposed methodology for aircraft trajectory forecasting is discussed in detail, accompanied by a literature review and an overview of the data preprocessing techniques used. The results demonstrate that the proposed meta-learner outperforms individual models in terms of accuracy, providing a more robust and proactive approach to improve operational safety in GA.展开更多
In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is use...In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is used to recognize the most similar datasets that have been performed by all of the candidate algorithms.By matching the most similar datasets we found,the corresponding performance of the candidate algorithms is used to generate recommendation to the user.The performance derives from a multi-criteria evaluation measure-ARR,which contains both accuracy and time.Furthermore,after applying Rough Set theory,we can find the redundant properties of the dataset.Thus,we can speed up the ranking process and increase the accuracy by using the reduct of the meta attributes.展开更多
Machine learning,especially deep learning,has been highly successful in data-intensive applications;however,the performance of these models will drop significantly when the amount of the training data amount does not ...Machine learning,especially deep learning,has been highly successful in data-intensive applications;however,the performance of these models will drop significantly when the amount of the training data amount does not meet the requirement.This leads to the so-called few-shot learning(FSL)problem,which requires the model rapidly generalize to new tasks that containing only a few labeled samples.In this paper,we proposed a new deep model,called deep convolutional meta-learning networks,to address the low performance of generalization under limited data for bearing fault diagnosis.The essential of our approach is to learn a base model from the multiple learning tasks using a support dataset and finetune the learnt parameters using few-shot tasks before it can adapt to the new learning task based on limited training data.The proposed method was compared to several FSL methods,including methods with and without pre-training the embedding mapping,and methods with finetuning the classifier or the whole model by utilizing the few-shot data from the target domain.The comparisons are carried out on 1-shot and 10-shot tasks using the Case Western Reserve University bearing dataset and a cylindrical roller bearing dataset.The experimental result illustrates that our method has good performance on the bearing fault diagnosis across various few-shot conditions.In addition,we found that the pretraining process does not always improve the prediction accuracy.展开更多
Although the deep-learning method has achieved great success for hyperspectral image(HsI)classification,the few-shot HsI classification deserves sufficient study because it is difficult and expensive to acquire labele...Although the deep-learning method has achieved great success for hyperspectral image(HsI)classification,the few-shot HsI classification deserves sufficient study because it is difficult and expensive to acquire labeled samples.In fact,the meta-learning methods can improve the per-formance for few-shot HSI classification effectively.However,most of the existing meta-learning methods for HsI classification are supervised,which still heavily rely on the labeled data for meta-training.Moreover,there are many cross-scene classification tasks in the real world,and domain adaptation of unsupervised meta-learning has been ignored for HsI classification so far.To address the above issues,this paper proposes an unsupervised meta-learning method with domain adap-tation based on a multi-task reconstruction-classification network(MRCN)for few-shot HSI classification.MRCN does not need any labeled data for meta-training,where the pseudo labels are generated by multiple spectral random sampling and data augmentation.The meta-training of MRCN jointly learns a shared encoding representation for two tasks and domains.On the one hand,we design an encoder-classifier to learn the classification task on the source-domain data.On the other hand,we devise an encoder-decoder to learn the reconstruction task on the target-domain data.The experimental results on four HSI datasets demonstrate that MRCN preforms better than several state-of-the-art methods with only two to five labeled samples per class.To the best of our knowledge,the proposed method is the first unsupervised meta-learning method that considers the domain adaptation for few-shot HSI classification.展开更多
Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for pre...Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for predicting mortality risk in patients with CVD,classifying them into high-risk and low-risk groups.Data were collected from 868 patients at Tabriz Heart Hospital(THH)in Iran,along with two open-access datasets—the Cleveland Heart Disease(CHD)and Faisalabad Institute of Cardiology(FIC)datasets.Data preprocessing involved class balancing via the Synthetic Minority Over-Sampling Technique(SMOTE).Each dataset was then split into training and test sets,and 5-fold cross-validation was employed to validate generalizability.Several machine-learning algorithms were stacked as base classifiers to generate meta-features,which were then input to a meta-learner combining their predictive strengths through soft voting.An ablation experiment was performed to identify the optimal configuration with two base classifiers—Random Forest(RF)and Support Vector Machine(SVM)—and two boosting classifiers—AdaBoost(ADB)and XGBoost(XGB).The model achieved 88%accuracy,91%AUC,and 79.1%sensitivity on the THH dataset;82.77%accuracy,89.37%AUC,and 93.72%sensitivity on the CHD dataset;and 81.8%accuracy,82.8%AUC and 78.8%sensitivity the FIC dataset,demonstrating the model’s generalizability across diverse datasets.To further enhance interpretability,Shapley Additive Explanations(SHAP)were applied to quantify each attribute’s contribution to predicted CVD risk,providing both global and local insights to help clinicians identify key risk factors and guide personalized care.展开更多
Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of backgrou...Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of background interference caused by continuous scene variations.The recently proposed segment anything model(SAM)has demonstrated exceptional performance in zero-shot segmentation tasks.The combination of SAM and vehicle Re-ID models can achieve efficient separation of vehicle identity and background information.This paper proposes a method that combines SAM-driven mask autoencoder(MAE)pre-training and backgroundaware meta-learning for unsupervised vehicle Re-ID.The method consists of three sub-modules.First,the segmentation capacity of SAM is utilized to separate the vehicle identity region from the background.SAM cannot be robustly employed in exceptional situations,such as those with ambiguity or occlusion.Thus,in vehicle Re-ID downstream tasks,a spatiallyconstrained vehicle background segmentation method is presented to obtain accurate background segmentation results.Second,SAM-driven MAE pre-training utilizes the aforementioned segmentation results to select patches belonging to the vehicle and to mask other patches,allowing MAE to learn identity-sensitive features in a self-supervised manner.Finally,we present a background-aware meta-learning method to fit varying degrees of background interference in different scenarios by combining different background region ratios.Our experiments demonstrate that the proposed method has state-of-the-art performance in reducing background interference variations.展开更多
With the advancement of deep learning techniques,the number of model parameters has been increasing,leading to significant memory consumption and limits in the deployment of such models in real-time applications.To re...With the advancement of deep learning techniques,the number of model parameters has been increasing,leading to significant memory consumption and limits in the deployment of such models in real-time applications.To reduce the number of model parameters and enhance the generalization capability of neural networks,we propose a method called Decoupled MetaDistil,which involves decoupled meta-distillation.This method utilizes meta-learning to guide the teacher model and dynamically adjusts the knowledge transfer strategy based on feedback from the student model,thereby improving the generalization ability.Furthermore,we introduce a decoupled loss method to explicitly transfer positive sample knowledge and explore the potential of negative samples knowledge.Extensive experiments demonstrate the effectiveness of our method.展开更多
Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing resources.However,the overwhelming ...Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing resources.However,the overwhelming upload traffic may lead to unacceptable uploading time.To tackle this issue,for tasks taking environmental data as input,the data perceived by roadside units(RSU)equipped with several sensors can be directly exploited for computation,resulting in a novel task offloading paradigm with integrated communications,sensing and computing(I-CSC).With this paradigm,vehicles can select to upload their sensed data to RSUs or transmit computing instructions to RSUs during the offloading.By optimizing the computation mode and network resources,in this paper,we investigate an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task.Although this nonconvex problem can be handled by the alternating minimization(AM)algorithm that alternatively minimizes the divided four sub-problems,it leads to high computational complexity and local optimal solution.To tackle this challenge,we propose a creative structural knowledge-driven meta-learning(SKDML)method,involving both the model-based AM algorithm and neural networks.Specifically,borrowing the iterative structure of the AM algorithm,also referred to as structural knowledge,the proposed SKDML adopts long short-term memory(LSTM)networkbased meta-learning to learn an adaptive optimizer for updating variables in each sub-problem,instead of the handcrafted counterpart in the AM algorithm.Furthermore,to pull out the solution from the local optimum,our proposed SKDML updates parameters in LSTM with the global loss function.Simulation results demonstrate that our method outperforms both the AM algorithm and the meta-learning without structural knowledge in terms of both the online processing time and the network performance.展开更多
基金supported by the ScientificResearch and Innovation Team Program of Sichuan University of Science and Technology(No.SUSE652A006)Sichuan Key Provincial Research Base of Intelligent Tourism(ZHYJ22-03)In addition,it is also listed as a project of Sichuan Provincial Science and Technology Programme(2022YFG0028).
文摘Emotion recognition plays a crucial role in various fields and is a key task in natural language processing (NLP). The objective is to identify and interpret emotional expressions in text. However, traditional emotion recognition approaches often struggle in few-shot cross-domain scenarios due to their limited capacity to generalize semantic features across different domains. Additionally, these methods face challenges in accurately capturing complex emotional states, particularly those that are subtle or implicit. To overcome these limitations, we introduce a novel approach called Dual-Task Contrastive Meta-Learning (DTCML). This method combines meta-learning and contrastive learning to improve emotion recognition. Meta-learning enhances the model’s ability to generalize to new emotional tasks, while instance contrastive learning further refines the model by distinguishing unique features within each category, enabling it to better differentiate complex emotional expressions. Prototype contrastive learning, in turn, helps the model address the semantic complexity of emotions across different domains, enabling the model to learn fine-grained emotions expression. By leveraging dual tasks, DTCML learns from two domains simultaneously, the model is encouraged to learn more diverse and generalizable emotions features, thereby improving its cross-domain adaptability and robustness, and enhancing its generalization ability. We evaluated the performance of DTCML across four cross-domain settings, and the results show that our method outperforms the best baseline by 5.88%, 12.04%, 8.49%, and 8.40% in terms of accuracy.
文摘The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource demands.Automated Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification tasks.This paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these limitations.Our method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature groups.The Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization problem.Empirical validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.
基金the National Key Research and Development Program of China(Grant No.2022YFB3302700)the National Natural Science Foundation of China(Grant No.52375486)the Shanghai Rising-Star Program(Grant No.22QB1404200).
文摘In intelligentmanufacturing processes such as aerospace production,computer numerical control(CNC)machine tools require real-time optimization of process parameters to meet precision machining demands.These dynamic operating conditions increase the risk of fatigue damage in CNC machine tool bearings,highlighting the urgent demand for rapid and accurate fault diagnosis methods that can maintain production efficiency and extend equipment uptime.However,varying conditions induce feature distribution shifts,and scarce fault samples limitmodel generalization.Therefore,this paper proposes a causal-Transformer-based meta-learning(CTML)method for bearing fault diagnosis in CNC machine tools,comprising three core modules:(1)the original bearing signal is transformed into a multi-scale time-frequency feature space using continuous wavelet transform;(2)a causal-Transformer architecture is designed to achieve feature extraction and fault classification based on the physical causal law of fault propagation;(3)the above mechanisms are integrated into a model-agnostic meta-learning(MAML)framework to achieve rapid cross-condition adaptation through an adaptive gradient pruning strategy.Experimental results using the multiple bearing dataset show that under few-shot cross-condition scenarios(3-way 1-shot and 3-way 5-shot),the proposed CTML outperforms benchmark models(e.g.,Transformer,domain adversarial neural networks(DANN),and MAML)in terms of classification accuracy and sensitivity to operating conditions,while maintaining a moderate level of model complexity.
基金supported by the National Key R&D Program of China under Grant No.2021ZD0110400.
文摘Many important problems in science and engineering require solving the so-called parametric partial differential equations(PDEs),i.e.,PDEs with different physical parameters,boundary conditions,shapes of computational domains,etc.Typical reduced order modeling techniques accelerate the solution of the parametric PDEs by projecting them onto a linear trial manifold constructed in the ofline stage.These methods often need a predefined mesh as well as a series of precomputed solution snapshots,and may struggle to balance between the efficiency and accuracy due to the limitation of the linear ansatz.Utilizing the nonlinear representation of neural networks(NNs),we propose the Meta-Auto-Decoder(MAD)to construct a nonlinear trial manifold,whose best possible performance is measured theoretically by the decoder width.Based on the meta-learning concept,the trial manifold can be learned in a mesh-free and unsupervised way during the pre-training stage.Fast adaptation to new(possibly heterogeneous)PDE parameters is enabled by searching on this trial manifold,and optionally fine-tuning the trial manifold at the same time.Extensive numerical experiments show that the MAD method exhibits a faster convergence speed without losing the accuracy than other deep learning-based methods.
文摘Meta-learning of dental X-rays is a machine learning technique that can be used to train models to perform new tasks quickly and with minimal input.Instead of just memorizing a task,this is accomplished through teaching a model how to learn.Algorithms for meta-learning are typically trained on a collection of training problems,each of which has a limited number of labelled instances.Multiple Xray classification tasks,including the detection of pneumonia,coronavirus disease 2019,and other disorders,have demonstrated the effectiveness of meta-learning.Meta-learning has the benefit of allowing models to be trained on dental X-ray datasets that are too few for more conventional machine learning methods.Due to the high cost and lengthy collection process associated with dental imaging datasets,this is significant for dental X-ray classification jobs.The ability to train models that are more resistant to fresh input is another benefit of meta-learning.
基金supported in part by the National Natural Science Foundation of China under Grant U1908212,62203432 and 92067205in part by the State Key Laboratory of Robotics of China under Grant 2023-Z03 and 2023-Z15in part by the Natural Science Foundation of Liaoning Province under Grant 2020-KF-11-02.
文摘The accurate and intelligent identification of the working conditions of a sucker-rod pumping system is necessary. As onshore oil extraction gradually enters its mid-to late-stage, the cost required to train a deep learning working condition recognition model for pumping wells by obtaining enough new working condition samples is expensive. For the few-shot problem and large calculation issues of new working conditions of oil wells, a working condition recognition method for pumping unit wells based on a 4-dimensional time-frequency signature (4D-TFS) and meta-learning convolutional shrinkage neural network (ML-CSNN) is proposed. First, the measured pumping unit well workup data are converted into 4D-TFS data, and the initial feature extraction task is performed while compressing the data. Subsequently, a convolutional shrinkage neural network (CSNN) with a specific structure that can ablate low-frequency features is designed to extract working conditions features. Finally, a meta-learning fine-tuning framework for learning the network parameters that are susceptible to task changes is merged into the CSNN to solve the few-shot issue. The results of the experiments demonstrate that the trained ML-CSNN has good recognition accuracy and generalization ability for few-shot working condition recognition. More specifically, in the case of lower computational complexity, only few-shot samples are needed to fine-tune the network parameters, and the model can be quickly adapted to new classes of well conditions.
基金supported by the Science and Technology Project of Jilin Provincial Department of Education[JJKH20210346KJ]the Capital Construction funds within the budget of Jilin Province in 2021(Innovation capacity construction)[2021C044-4]the Jilin Province Science and Technology Development Plan Project[20210101185JC].
文摘Currently,one of the most severe problems in the agricultural industry is the effect of diseases and pests on global crop production and economic development.Therefore,further research in the field of crop disease and pest detection is necessary to address the mentioned problem.Aiming to identify the diseased crops and insect pests timely and accurately and perform appropriate prevention measures to reduce the associated losses,this article proposes a Model-Agnostic Meta-Learning(MAML)attention model based on the meta-learning paradigm.The proposed model combines meta-learning with basic learning and adopts an Efficient Channel Attention(ECA)mod-ule.The module follows the local cross-channel interactive strategy of non-dimensional reduction to strengthen the weight parameters corresponding to certain disease characteristics.The proposed meta-learning-based algorithm has the advantage of strong generalization capability and,by integrating the ECA module in the original model,can achieve more efficient detection in new tasks.The proposed model is verified by experiments,and the experimental results show that compared with the original MAML model,the proposed improved MAML-Attention model has a better performance by 1.8–9.31 percentage points in different classification tasks;the maximum accuracy is increased by 1.15–8.2 percentage points.The experimental results verify the strong generalization ability and good robustness of the proposed MAML-Attention model.Compared to the other few-shot methods,the proposed MAML-Attention performs better.
基金supported by Hebei Province Natural Science Fund for Distinguished Young Scholars (NO.E2020209082).
文摘In recent years,machine learning has made great progress in intrusion detection,network protection,anomaly detection,and other issues in cyberspace.However,these traditional machine learning algorithms usually require a lot of data to learn and have a low recognition rate for unknown attacks.Among them,“one-shot learning”,“few-shot learning”,and“zero-shot learning”are challenges that cannot be ignored for traditional machine learning.The more intractable problem in cyberspace security is the changeable attack mode.When a new attack mode appears,there are few or even zero samples that can be learned.Meta-learning comes from imitating human problem-solving methods as humans can quickly learn unknown things based on their existing knowledge when learning.Its purpose is to quickly obtain a model with high accuracy and strong generalization through less data training.This article first divides the meta-learning model into five research directions based on different principles of use.They are model-based,metric-based,optimization-based,online-learning-based,or stacked ensemble-based.Then,the current problems in the field of cyberspace security are categorized into three branches:cyber security,information security,and artificial intelligence security according to different perspectives.Then,the application research results of various meta-learning models on these three branches are reviewed.At the same time,based on the characteristics of strong generalization,evolution,and scalability of meta-learning,we contrast and summarize its advantages in solving problems.Finally,the prospect of future deep application of meta-learning in the field of cyberspace security is summarized.
文摘capacity and creativity tendencies among Chinese baccalaureate nursing students.Design:Cross-sectional study design.Methods:A convenient sample of 445 baccalaureate nursing students were surveyed in two universities in Tianjin,China.Students completed a questionnaire that included their demographic information,Achievement Motivation Scale,Meta-Learning Capacity Questionnaire,and Creativity Tendencies Scale.Pearson correlation was performed to test the correlation among achievement motivation,meta-learning capacity and creativity tendencies.Hierarchical linear regression analyses were performed to explore the mediating role of meta-learning capacity.Results:The participants had moderate levels of achievement motivation(mean score 2.383±0.240)and meta-learning capacity(mean score 1.505±0.241)and a medium-high level of creativity tendency(mean score 1.841±0.288).Creativity tendencies was significantly associated with both achievement motivation and meta-learning capacity(both P<0.01).Furthermore,meta-learning capacity mediated the relationship between achievement motivation and high creativity tendencies.Conclusion:The study hypotheses were supported.Higher achievement motivation,and meta-learning capacity can increase creativity tendencies of baccalaureate nursing students,and meta-learning capacity was found to mediate the relationship between achievement motivation and creativity tendencies.Nursing educators should pay attention to the positive role of meta-learning capacity in nursing students’learning,and make them more confident when they finish their studies.
基金Supported by the National Natural Science Foundation of China(No.61171131)the Key R&D Program of Shandong Province(No.YD01033)the China Scholarship Council Project(No.021608370049).
文摘Meta-learning provides a framework for the possibility of mimicking artificial intelligence.How-ever,data distribution of the training set fails to be consistent with the one of the testing set as the limited domain differences among them.These factors often result in poor generalization in existing meta-learning models.In this work,a novel smoother manifold for graph meta-learning(SGML)is proposed,which derives the similarity parameters of node features from the relationship between nodes and edges in the graph structure,and then utilizes the similarity parameters to yield smoother manifold through embedded propagation module.Smoother manifold can naturally filter out noise from the most important components when generalizing the local mapping relationship to the global.Besides suiting for generalizing on unseen low data issues,the framework is capable to easily perform transductive inference.Experimental results on MiniImageNet and TieredImageNet consistently show that applying SGML to supervised and semi-supervised classification can improve the performance in reducing the noise of domain shift representation.
文摘Meta-learning algorithms learn about the learning process itself so it can speed up subsequent similar learning tasks with fewer data and iterations. If achieved, these benefits expand the flexibility of traditional machine learning to areas where there are small windows of time or data available. One such area is stock trading, where the relevance of data decreases as time passes, requiring fast results on fewer data points to respond to fast-changing market trends. We, to the best of our knowledge, are the first to apply meta-learning algorithms to an evolutionary strategy for stock trading to decrease learning time by using fewer iterations and to achieve higher trading profits with fewer data points. We found that our meta-learning approach to stock trading earns profits similar to a purely evolutionary algorithm. However, it only requires 50 iterations during test, versus thousands that are typically required without meta-learning, or 50% of the training data during test.
文摘The aviation industry has seen significant advancements in safety procedures over the past few decades, resulting in a steady decline in aviation deaths worldwide. However, the safety standards in General Aviation (GA) are still lower compared to those in commercial aviation. With the anticipated growth in air travel, there is an imminent need to improve operational safety in GA. One way to improve aircraft and operational safety is through trajectory prediction. Trajectory prediction plays a key role in optimizing air traffic control and improving overall flight safety. This paper proposes a meta-learning approach to predict short- to mid-term trajectories of aircraft using historical real flight data collected from multiple GA aircraft. The proposed solution brings together multiple models to improve prediction accuracy. In this paper, we are combining two models, Random Forest Regression (RFR) and Long Short-term Memory (LSTM), using k-Nearest Neighbors (k-NN), to output the final prediction based on the combined output of the individual models. This approach gives our model an edge over single-model predictions. We present the results of our meta-learner and evaluate its performance against individual models using the Mean Absolute Error (MAE), Absolute Altitude Error (AAE), and Root Mean Squared Error (RMSE) evaluation metrics. The proposed methodology for aircraft trajectory forecasting is discussed in detail, accompanied by a literature review and an overview of the data preprocessing techniques used. The results demonstrate that the proposed meta-learner outperforms individual models in terms of accuracy, providing a more robust and proactive approach to improve operational safety in GA.
文摘In this paper,we propose a Rough Set assisted Meta-Learning method on how to select the most-suited machine-learning algorithms with minimal effort for a new given dataset. A k-Nearest Neighbor (k-NN) algorithm is used to recognize the most similar datasets that have been performed by all of the candidate algorithms.By matching the most similar datasets we found,the corresponding performance of the candidate algorithms is used to generate recommendation to the user.The performance derives from a multi-criteria evaluation measure-ARR,which contains both accuracy and time.Furthermore,after applying Rough Set theory,we can find the redundant properties of the dataset.Thus,we can speed up the ranking process and increase the accuracy by using the reduct of the meta attributes.
基金This research was funded by RECLAIM project“Remanufacturing and Refurbishment of Large Industrial Equipment”and received funding from the European Commission Horizon 2020 research and innovation program under Grant Agreement No.869884The authors also acknowledge the support of The Efficiency and Performance Engineering Network International Collaboration Fund Award 2022(TEPEN-ICF 2022)project“Intelligent Fault Diagnosis Method and System with Few-Shot Learning Technique under Small Sample Data Condition”.
文摘Machine learning,especially deep learning,has been highly successful in data-intensive applications;however,the performance of these models will drop significantly when the amount of the training data amount does not meet the requirement.This leads to the so-called few-shot learning(FSL)problem,which requires the model rapidly generalize to new tasks that containing only a few labeled samples.In this paper,we proposed a new deep model,called deep convolutional meta-learning networks,to address the low performance of generalization under limited data for bearing fault diagnosis.The essential of our approach is to learn a base model from the multiple learning tasks using a support dataset and finetune the learnt parameters using few-shot tasks before it can adapt to the new learning task based on limited training data.The proposed method was compared to several FSL methods,including methods with and without pre-training the embedding mapping,and methods with finetuning the classifier or the whole model by utilizing the few-shot data from the target domain.The comparisons are carried out on 1-shot and 10-shot tasks using the Case Western Reserve University bearing dataset and a cylindrical roller bearing dataset.The experimental result illustrates that our method has good performance on the bearing fault diagnosis across various few-shot conditions.In addition,we found that the pretraining process does not always improve the prediction accuracy.
基金supported by the National Natural Science Foundation of China(62077038,61672405,62176196 and 62271374).
文摘Although the deep-learning method has achieved great success for hyperspectral image(HsI)classification,the few-shot HsI classification deserves sufficient study because it is difficult and expensive to acquire labeled samples.In fact,the meta-learning methods can improve the per-formance for few-shot HSI classification effectively.However,most of the existing meta-learning methods for HsI classification are supervised,which still heavily rely on the labeled data for meta-training.Moreover,there are many cross-scene classification tasks in the real world,and domain adaptation of unsupervised meta-learning has been ignored for HsI classification so far.To address the above issues,this paper proposes an unsupervised meta-learning method with domain adap-tation based on a multi-task reconstruction-classification network(MRCN)for few-shot HSI classification.MRCN does not need any labeled data for meta-training,where the pseudo labels are generated by multiple spectral random sampling and data augmentation.The meta-training of MRCN jointly learns a shared encoding representation for two tasks and domains.On the one hand,we design an encoder-classifier to learn the classification task on the source-domain data.On the other hand,we devise an encoder-decoder to learn the reconstruction task on the target-domain data.The experimental results on four HSI datasets demonstrate that MRCN preforms better than several state-of-the-art methods with only two to five labeled samples per class.To the best of our knowledge,the proposed method is the first unsupervised meta-learning method that considers the domain adaptation for few-shot HSI classification.
文摘Cardiovascular diseases(CVD)remain a leading cause of mortality worldwide,highlighting the need for precise risk assessment tools to support clinical decision-making.This study introduces a meta-learning model for predicting mortality risk in patients with CVD,classifying them into high-risk and low-risk groups.Data were collected from 868 patients at Tabriz Heart Hospital(THH)in Iran,along with two open-access datasets—the Cleveland Heart Disease(CHD)and Faisalabad Institute of Cardiology(FIC)datasets.Data preprocessing involved class balancing via the Synthetic Minority Over-Sampling Technique(SMOTE).Each dataset was then split into training and test sets,and 5-fold cross-validation was employed to validate generalizability.Several machine-learning algorithms were stacked as base classifiers to generate meta-features,which were then input to a meta-learner combining their predictive strengths through soft voting.An ablation experiment was performed to identify the optimal configuration with two base classifiers—Random Forest(RF)and Support Vector Machine(SVM)—and two boosting classifiers—AdaBoost(ADB)and XGBoost(XGB).The model achieved 88%accuracy,91%AUC,and 79.1%sensitivity on the THH dataset;82.77%accuracy,89.37%AUC,and 93.72%sensitivity on the CHD dataset;and 81.8%accuracy,82.8%AUC and 78.8%sensitivity the FIC dataset,demonstrating the model’s generalizability across diverse datasets.To further enhance interpretability,Shapley Additive Explanations(SHAP)were applied to quantify each attribute’s contribution to predicted CVD risk,providing both global and local insights to help clinicians identify key risk factors and guide personalized care.
基金supported by the National Natural Science Foundation of China under Grant Nos.62076117 and 62166026the Jiangxi Nos.20224BAB212011,20232BAB212008,and 20232BAB202051.
文摘Distinguishing identity-unrelated background information from discriminative identity information poses a challenge in unsupervised vehicle re-identification(Re-ID).Re-ID models suffer from varying degrees of background interference caused by continuous scene variations.The recently proposed segment anything model(SAM)has demonstrated exceptional performance in zero-shot segmentation tasks.The combination of SAM and vehicle Re-ID models can achieve efficient separation of vehicle identity and background information.This paper proposes a method that combines SAM-driven mask autoencoder(MAE)pre-training and backgroundaware meta-learning for unsupervised vehicle Re-ID.The method consists of three sub-modules.First,the segmentation capacity of SAM is utilized to separate the vehicle identity region from the background.SAM cannot be robustly employed in exceptional situations,such as those with ambiguity or occlusion.Thus,in vehicle Re-ID downstream tasks,a spatiallyconstrained vehicle background segmentation method is presented to obtain accurate background segmentation results.Second,SAM-driven MAE pre-training utilizes the aforementioned segmentation results to select patches belonging to the vehicle and to mask other patches,allowing MAE to learn identity-sensitive features in a self-supervised manner.Finally,we present a background-aware meta-learning method to fit varying degrees of background interference in different scenarios by combining different background region ratios.Our experiments demonstrate that the proposed method has state-of-the-art performance in reducing background interference variations.
基金supported by the Key R&D Program of Shandong Province,China(2022CXGC20106)the Pilot Project for Integrated Innovation of Science,Education,and Industry of Qilu University of Technology(Shandong Academy of Sciences)(2022JBZ01-01)+1 种基金Joint Fund of Shandong Natural Science Foundation(ZR2022LZH010)Shandong Provincial Natural Science Foundation(ZR2021LZH008).
文摘With the advancement of deep learning techniques,the number of model parameters has been increasing,leading to significant memory consumption and limits in the deployment of such models in real-time applications.To reduce the number of model parameters and enhance the generalization capability of neural networks,we propose a method called Decoupled MetaDistil,which involves decoupled meta-distillation.This method utilizes meta-learning to guide the teacher model and dynamically adjusts the knowledge transfer strategy based on feedback from the student model,thereby improving the generalization ability.Furthermore,we introduce a decoupled loss method to explicitly transfer positive sample knowledge and explore the potential of negative samples knowledge.Extensive experiments demonstrate the effectiveness of our method.
基金supported in part by National Key Research and Development Program of China(2020YFB1807700)in part by National Natural Science Foundation of China(62201414)+2 种基金in part by Qinchuangyuan Project(OCYRCXM-2022-362)in part by Science and Technology Project of Guangzhou(2023A04J1741)in part by Chongqing key laboratory of Mobile Communications Technologg(cqupt-mct-202202).
文摘Task offloading is a potential solution to satisfy the strict requirements of computation-intensive and latency-sensitive vehicular applications due to the limited onboard computing resources.However,the overwhelming upload traffic may lead to unacceptable uploading time.To tackle this issue,for tasks taking environmental data as input,the data perceived by roadside units(RSU)equipped with several sensors can be directly exploited for computation,resulting in a novel task offloading paradigm with integrated communications,sensing and computing(I-CSC).With this paradigm,vehicles can select to upload their sensed data to RSUs or transmit computing instructions to RSUs during the offloading.By optimizing the computation mode and network resources,in this paper,we investigate an I-CSC-based task offloading problem to reduce the cost caused by resource consumption while guaranteeing the latency of each task.Although this nonconvex problem can be handled by the alternating minimization(AM)algorithm that alternatively minimizes the divided four sub-problems,it leads to high computational complexity and local optimal solution.To tackle this challenge,we propose a creative structural knowledge-driven meta-learning(SKDML)method,involving both the model-based AM algorithm and neural networks.Specifically,borrowing the iterative structure of the AM algorithm,also referred to as structural knowledge,the proposed SKDML adopts long short-term memory(LSTM)networkbased meta-learning to learn an adaptive optimizer for updating variables in each sub-problem,instead of the handcrafted counterpart in the AM algorithm.Furthermore,to pull out the solution from the local optimum,our proposed SKDML updates parameters in LSTM with the global loss function.Simulation results demonstrate that our method outperforms both the AM algorithm and the meta-learning without structural knowledge in terms of both the online processing time and the network performance.
