Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy cl...Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.展开更多
In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentba...In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.展开更多
Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,lim...Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,limited by the fragmented data and loss of contextual information,the generated reports are prone to the problems such as content redundancy and omission of critical information,failing to meet the demands of efficient decision-making and accurate management in modern power systems.To address these issues,this paper proposes a knowledge graph(KG)-enhanced framework to automatically generate electric power engineering reports.In the KG construction phase,a feature-fused entity recognition model named BERT-BiLSTM-CRF is adopted to improve the accuracy of entity recognition in scenarios involving power engineering professional terminology,thereby solving the problem of ambiguous entity boundaries in traditional models;then a BERT-attention relation extraction model is proposed to enhance the completeness of extracting complex hierarchical and implicit relations in power grid data.In the report generation phase,an improved Transformer architecture is adopted to accurately transform structured knowledge into natural language reports that comply with engineering specifications,addressing the issue of semantic inconsistency caused by the loss of structural information in existing models.By validating with real-world projects,the results show that the proposed framework significantly outperforms existing baseline models in entity recognition,confirming its superiority and applicability in practical engineering.展开更多
A constrained partial permutation strategy is proposed for matching spatial relation graph (SRG), which is used in our sketch input and recognition system Smart Sketchpad for representing the spatial relationship amon...A constrained partial permutation strategy is proposed for matching spatial relation graph (SRG), which is used in our sketch input and recognition system Smart Sketchpad for representing the spatial relationship among the components of a graphic object. Using two kinds of matching constraints dynamically generated in the matching process, the proposed approach can prune most improper mappings between SRGs during the matching process. According to our theoretical analysis in this paper, the time complexity of our approach is O(n 2) in the best case, and O(n!) in the worst case, which occurs infrequently. The spatial complexity is always O(n) for all cases. Implemented in Smart Sketchpad, our proposed strategy is of good performance.展开更多
An integrated approach to generation of precedence relations and precedencegraphs for assembly sequence planning is presented, which contains more assembly flexibility. Theapproach involves two stages. Based on the as...An integrated approach to generation of precedence relations and precedencegraphs for assembly sequence planning is presented, which contains more assembly flexibility. Theapproach involves two stages. Based on the assembly model, the components in the assembly can bedivided into partially constrained components and completely con-strained components in the firststage, and then geometric precedence relation for every component is generated automatically.According to the result of the first stage, the second stage determines and constructs allprecedence graphs. The algorithms of these two stages proposed are verified by two assemblyexamples.展开更多
Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,rese...Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.展开更多
Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread a...Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.展开更多
Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,...Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.展开更多
The relation is a semantic expression relevant to two named entities in a sentence.Since a sentence usually contains several named entities,it is essential to learn a structured sentence representation that encodes de...The relation is a semantic expression relevant to two named entities in a sentence.Since a sentence usually contains several named entities,it is essential to learn a structured sentence representation that encodes dependency information specific to the two named entities.In related work,graph convolutional neural networks are widely adopted to learn semantic dependencies,where a dependency tree initializes the adjacency matrix.However,this approach has two main issues.First,parsing a sentence heavily relies on external toolkits,which can be errorprone.Second,the dependency tree only encodes the syntactical structure of a sentence,which may not align with the relational semantic expression.In this paper,we propose an automatic graph learningmethod to autonomously learn a sentence’s structural information.Instead of using a fixed adjacency matrix initialized by a dependency tree,we introduce an Adaptive Adjacency Matrix to encode the semantic dependency between tokens.The elements of thismatrix are dynamically learned during the training process and optimized by task-relevant learning objectives,enabling the construction of task-relevant semantic dependencies within a sentence.Our model demonstrates superior performance on the TACRED and SemEval 2010 datasets,surpassing previous works by 1.3%and 0.8%,respectively.These experimental results show that our model excels in the relation extraction task,outperforming prior models.展开更多
Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatical...Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.展开更多
The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G ...The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G is defined as ME(G) = Pni=1 |λi|. By the famous Coulson’s formula, matching energies can also be calculated by an improper integral depending on a parameter. A k-claw attaching graph Gu(k) refers to the graph obtained by attaching k pendent edges to the graph G at the vertex u, where u is called the root of Gu(k). In this paper, we use some theories of mathematical analysis to obtain a new technique to compare the matching energies of two k-claw attaching graphs Gu(k) and Hv(k) with the same order, that is, limk→∞[ME(Gu(k)) − ME(Hv(k))] = ME(G − u) − ME(H − v). By the technique, we finally determine unicyclic graphs of order n with the 9th to 13th minimal matching energies for all n ≥ 58.展开更多
Collecting amounts of distorted/clean image pairs in the real world is non-trivial,which severely limits the practical application of these supervised learning-based methods to real-world image super-resolution(RealSR...Collecting amounts of distorted/clean image pairs in the real world is non-trivial,which severely limits the practical application of these supervised learning-based methods to real-world image super-resolution(RealSR).Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples.However,these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images.To overcome this problem,we are the first to take a close look at the under-explored direction for RealSR,i.e.,few-shot real-world image super-resolution,which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs.Under this brand-new scenario,we propose distortion relation guided transfer learning(DRTL)for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions(i.e.,synthetic distortions)to the target RealSR under the guidance of the distortion relation.Concretely,DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion(i.e.,real distortions in RealSR).Based on the distortion relation,DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions.In this way,DRTL is able to quickly learn the most relevant knowledge from the synthetic distortions for the target distortion.We instantiate DRTL with two commonly-used transfer learning paradigms,including pretraining and meta-learning pipelines,to realize a distortion relation-aware few-shot RealSR.Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL.展开更多
In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with l...In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.展开更多
Converting relational data into a property graph is advantageous for relational data analysis using graph algorithms.However,existing methods for constructing property graphs from relational data often require complex...Converting relational data into a property graph is advantageous for relational data analysis using graph algorithms.However,existing methods for constructing property graphs from relational data often require complex join operations when predefined entities and relationships are given.Additionally,constructing graphs from large-scale relational data is time-consuming due to the need to aggregate instances from multiple tables.To address this issue,this paper proposes a schema-based graph construction method called GraphCon.GraphCon employs a schema-based mapping mechanism to achieve equivalent mapping between the graph schema and the relational schema.Additionally,we optimize a complex join strategy,InstanceJoin,in the graph construction process.To improve efficiency in handling large-scale data,we introduce a parallel algorithm that includes a data partition strategy based on the graph schema and a load-balancing strategy to enhance scalability.Experiments using the TPC-H benchmark and real-life datasets validate the efficiency and scalability of our proposed methods.展开更多
基金funded by the Research Project:THTETN.05/24-25,VietnamAcademy of Science and Technology.
文摘Multi-view clustering is a critical research area in computer science aimed at effectively extracting meaningful patterns from complex,high-dimensional data that single-view methods cannot capture.Traditional fuzzy clustering techniques,such as Fuzzy C-Means(FCM),face significant challenges in handling uncertainty and the dependencies between different views.To overcome these limitations,we introduce a new multi-view fuzzy clustering approach that integrates picture fuzzy sets with a dual-anchor graph method for multi-view data,aiming to enhance clustering accuracy and robustness,termed Multi-view Picture Fuzzy Clustering(MPFC).In particular,the picture fuzzy set theory extends the capability to represent uncertainty by modeling three membership levels:membership degrees,neutral degrees,and refusal degrees.This allows for a more flexible representation of uncertain and conflicting data than traditional fuzzy models.Meanwhile,dual-anchor graphs exploit the similarity relationships between data points and integrate information across views.This combination improves stability,scalability,and robustness when handling noisy and heterogeneous data.Experimental results on several benchmark datasets demonstrate significant improvements in clustering accuracy and efficiency,outperforming traditional methods.Specifically,the MPFC algorithm demonstrates outstanding clustering performance on a variety of datasets,attaining a Purity(PUR)score of 0.6440 and an Accuracy(ACC)score of 0.6213 for the 3 Sources dataset,underscoring its robustness and efficiency.The proposed approach significantly contributes to fields such as pattern recognition,multi-view relational data analysis,and large-scale clustering problems.Future work will focus on extending the method for semi-supervised multi-view clustering,aiming to enhance adaptability,scalability,and performance in real-world applications.
文摘In the era of exponential growth of digital information,recommender algorithms are vital for helping users navigate vast data to find relevant items.Traditional approaches such as collaborative filtering and contentbasedmethods have limitations in capturing complex,multi-faceted relationships in large-scale,sparse datasets.Recent advances in Graph Neural Networks(GNNs)have significantly improved recommendation performance by modeling high-order connection patterns within user-item interaction networks.However,existing GNN-based models like LightGCN and NGCF focus primarily on single-type interactions and often overlook diverse semantic relationships,leading to reduced recommendation diversity and limited generalization.To address these challenges,this paper proposes a dual multi-relational graph neural network recommendation algorithm based on relational interactions.Our approach constructs two complementary graph structures:a User-Item Interaction Graph(UIIG),which explicitly models direct user behaviors such as clicks and purchases,and a Relational Association Graph(RAG),which uncovers latent associations based on user similarities and item attributes.The proposed Dual Multi-relational Graph Neural Network(DMGNN)features two parallel branches that perform multi-layer graph convolutional operations,followed by an adaptive fusion mechanism to effectively integrate information from both graphs.This design enhances the model’s capacity to capture diverse relationship types and complex relational patterns.Extensive experiments conducted on benchmark datasets—including MovieLens-1M,Amazon-Electronics,and Yelp—demonstrate thatDMGNN outperforms state-of-the-art baselines,achieving improvements of up to 12.3%in Precision,9.7%in Recall,and 11.5%in F1 score.Moreover,DMGNN significantly boosts recommendation diversity by 15.2%,balancing accuracy with exploration.These results highlight the effectiveness of leveraging hierarchical multi-relational information,offering a promising solution to the challenges of data sparsity and relation heterogeneity in recommendation systems.Our work advances the theoretical understanding of multi-relational graph modeling and presents practical insights for developing more personalized,diverse,and robust recommender systems.
基金supported by State Grid Shanghai Economic Research Institute under Grant No.SGTYHT/23-JS-004.
文摘Due to the complex structural hierarchy,with deeply nested associative relations between entities such as equipment,specifications,and business processes,intelligent power grid engineering is challenging.Meanwhile,limited by the fragmented data and loss of contextual information,the generated reports are prone to the problems such as content redundancy and omission of critical information,failing to meet the demands of efficient decision-making and accurate management in modern power systems.To address these issues,this paper proposes a knowledge graph(KG)-enhanced framework to automatically generate electric power engineering reports.In the KG construction phase,a feature-fused entity recognition model named BERT-BiLSTM-CRF is adopted to improve the accuracy of entity recognition in scenarios involving power engineering professional terminology,thereby solving the problem of ambiguous entity boundaries in traditional models;then a BERT-attention relation extraction model is proposed to enhance the completeness of extracting complex hierarchical and implicit relations in power grid data.In the report generation phase,an improved Transformer architecture is adopted to accurately transform structured knowledge into natural language reports that comply with engineering specifications,addressing the issue of semantic inconsistency caused by the loss of structural information in existing models.By validating with real-world projects,the results show that the proposed framework significantly outperforms existing baseline models in entity recognition,confirming its superiority and applicability in practical engineering.
文摘A constrained partial permutation strategy is proposed for matching spatial relation graph (SRG), which is used in our sketch input and recognition system Smart Sketchpad for representing the spatial relationship among the components of a graphic object. Using two kinds of matching constraints dynamically generated in the matching process, the proposed approach can prune most improper mappings between SRGs during the matching process. According to our theoretical analysis in this paper, the time complexity of our approach is O(n 2) in the best case, and O(n!) in the worst case, which occurs infrequently. The spatial complexity is always O(n) for all cases. Implemented in Smart Sketchpad, our proposed strategy is of good performance.
基金This project is supported by National Natural Science Foundation of China(No.59990470,No.59725514,No.59985004)and Robotics Laboratory,Chinese Academy of Sciences Foundation(No.RL200006)
文摘An integrated approach to generation of precedence relations and precedencegraphs for assembly sequence planning is presented, which contains more assembly flexibility. Theapproach involves two stages. Based on the assembly model, the components in the assembly can bedivided into partially constrained components and completely con-strained components in the firststage, and then geometric precedence relation for every component is generated automatically.According to the result of the first stage, the second stage determines and constructs allprecedence graphs. The algorithms of these two stages proposed are verified by two assemblyexamples.
基金supported by the Major Project of the National Natural Science Foundation of China (82090051,81871442)Outstanding Member Project of Youth Innovation Promotion Association of the Chinese Academy of Sciences (Y201930)。
文摘Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.
文摘Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.
文摘Deep neural network-based relational extraction research has made significant progress in recent years,andit provides data support for many natural language processing downstream tasks such as building knowledgegraph,sentiment analysis and question-answering systems.However,previous studies ignored much unusedstructural information in sentences that could enhance the performance of the relation extraction task.Moreover,most existing dependency-based models utilize self-attention to distinguish the importance of context,whichhardly deals withmultiple-structure information.To efficiently leverage multiple structure information,this paperproposes a dynamic structure attention mechanism model based on textual structure information,which deeplyintegrates word embedding,named entity recognition labels,part of speech,dependency tree and dependency typeinto a graph convolutional network.Specifically,our model extracts text features of different structures from theinput sentence.Textual Structure information Graph Convolutional Networks employs the dynamic structureattention mechanism to learn multi-structure attention,effectively distinguishing important contextual features invarious structural information.In addition,multi-structure weights are carefully designed as amergingmechanismin the different structure attention to dynamically adjust the final attention.This paper combines these featuresand trains a graph convolutional network for relation extraction.We experiment on supervised relation extractiondatasets including SemEval 2010 Task 8,TACRED,TACREV,and Re-TACED,the result significantly outperformsthe previous.
基金supported by the Technology Projects of Guizhou Province under Grant[2024]003National Natural Science Foundation of China(GrantNos.62166007,62066008,62066007)Guizhou Provincial Science and Technology Projects under Grant No.ZK[2023]300.
文摘The relation is a semantic expression relevant to two named entities in a sentence.Since a sentence usually contains several named entities,it is essential to learn a structured sentence representation that encodes dependency information specific to the two named entities.In related work,graph convolutional neural networks are widely adopted to learn semantic dependencies,where a dependency tree initializes the adjacency matrix.However,this approach has two main issues.First,parsing a sentence heavily relies on external toolkits,which can be errorprone.Second,the dependency tree only encodes the syntactical structure of a sentence,which may not align with the relational semantic expression.In this paper,we propose an automatic graph learningmethod to autonomously learn a sentence’s structural information.Instead of using a fixed adjacency matrix initialized by a dependency tree,we introduce an Adaptive Adjacency Matrix to encode the semantic dependency between tokens.The elements of thismatrix are dynamically learned during the training process and optimized by task-relevant learning objectives,enabling the construction of task-relevant semantic dependencies within a sentence.Our model demonstrates superior performance on the TACRED and SemEval 2010 datasets,surpassing previous works by 1.3%and 0.8%,respectively.These experimental results show that our model excels in the relation extraction task,outperforming prior models.
文摘Given the scarcity of Satellite Frequency and Orbit(SFO)resources,it holds paramount importance to establish a comprehensive knowledge graph of SFO field(SFO-KG)and employ knowledge reasoning technology to automatically mine available SFO resources.An essential aspect of constructing SFO-KG is the extraction of Chinese entity relations.Unfortunately,there is currently no publicly available Chinese SFO entity Relation Extraction(RE)dataset.Moreover,publicly available SFO text data contain numerous NA(representing for“No Answer”)relation category sentences that resemble other relation sentences and pose challenges in accurate classification,resulting in low recall and precision for the NA relation category in entity RE.Consequently,this issue adversely affects both the accuracy of constructing the knowledge graph and the efficiency of RE processes.To address these challenges,this paper proposes a method for extracting Chinese SFO text entity relations based on dynamic integrated learning.This method includes the construction of a manually annotated Chinese SFO entity RE dataset and a classifier combining features of SFO resource data.The proposed approach combines integrated learning and pre-training models,specifically utilizing Bidirectional Encoder Representation from Transformers(BERT).In addition,it incorporates one-class classification,attention mechanisms,and dynamic feedback mechanisms to improve the performance of the RE model.Experimental results show that the proposed method outperforms the traditional methods in terms of F1 value when extracting entity relations from both balanced and long-tailed datasets.
基金Supported by the National Natural Science Foundation of China(Nos.12271439,11871398)the National College Students Innovation and Entrepreneurship Training Program(No.201910699173)。
文摘The concept of matching energy was proposed by Gutman and Wagner firstly in 2012. Let G be a simple graph of order n and λ1, λ2, . . . , λn be the zeros of its matching polynomial. The matching energy of a graph G is defined as ME(G) = Pni=1 |λi|. By the famous Coulson’s formula, matching energies can also be calculated by an improper integral depending on a parameter. A k-claw attaching graph Gu(k) refers to the graph obtained by attaching k pendent edges to the graph G at the vertex u, where u is called the root of Gu(k). In this paper, we use some theories of mathematical analysis to obtain a new technique to compare the matching energies of two k-claw attaching graphs Gu(k) and Hv(k) with the same order, that is, limk→∞[ME(Gu(k)) − ME(Hv(k))] = ME(G − u) − ME(H − v). By the technique, we finally determine unicyclic graphs of order n with the 9th to 13th minimal matching energies for all n ≥ 58.
基金supported by the National Natural Science Foundation of China(623B2098,62021001,62371434)the Postdoctoral Fellowship Program of CPSF(GZC20252293)+1 种基金the China Postdoctoral Science Foundation–Anhui Joint Support Program(2024T017AH)Anhui Postdoctoral Scientific Research Program Foundation(2025A1015).
文摘Collecting amounts of distorted/clean image pairs in the real world is non-trivial,which severely limits the practical application of these supervised learning-based methods to real-world image super-resolution(RealSR).Previous works usually address this problem by leveraging unsupervised learning-based technologies to alleviate the dependency on paired training samples.However,these methods typically suffer from unsatisfactory texture synthesis due to the lack of supervision of clean images.To overcome this problem,we are the first to take a close look at the under-explored direction for RealSR,i.e.,few-shot real-world image super-resolution,which aims to tackle the challenging RealSR problem with few-shot distorted/clean image pairs.Under this brand-new scenario,we propose distortion relation guided transfer learning(DRTL)for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions(i.e.,synthetic distortions)to the target RealSR under the guidance of the distortion relation.Concretely,DRTL builds a knowledge graph to capture the distortion relation between auxiliary distortions and target distortion(i.e.,real distortions in RealSR).Based on the distortion relation,DRTL adopts a gradient reweighting strategy to guide the knowledge transfer process between auxiliary distortions and target distortions.In this way,DRTL is able to quickly learn the most relevant knowledge from the synthetic distortions for the target distortion.We instantiate DRTL with two commonly-used transfer learning paradigms,including pretraining and meta-learning pipelines,to realize a distortion relation-aware few-shot RealSR.Extensive experiments on multiple benchmarks and thorough ablation studies demonstrate the effectiveness of our DRTL.
基金supported by the National Science and Technology Council(NSTC),Taiwan,under Grants Numbers 112-2622-E-029-009 and 112-2221-E-029-019.
文摘In the domain of knowledge graph embedding,conventional approaches typically transform entities and relations into continuous vector spaces.However,parameter efficiency becomes increasingly crucial when dealing with large-scale knowledge graphs that contain vast numbers of entities and relations.In particular,resource-intensive embeddings often lead to increased computational costs,and may limit scalability and adaptability in practical environ-ments,such as in low-resource settings or real-world applications.This paper explores an approach to knowledge graph representation learning that leverages small,reserved entities and relation sets for parameter-efficient embedding.We introduce a hierarchical attention network designed to refine and maximize the representational quality of embeddings by selectively focusing on these reserved sets,thereby reducing model complexity.Empirical assessments validate that our model achieves high performance on the benchmark dataset with fewer parameters and smaller embedding dimensions.The ablation studies further highlight the impact and contribution of each component in the proposed hierarchical attention structure.
基金supported by the National Natural Science Foundation of China(No.61902274)the Outstanding Young Talent Program of Beijing Municipal Universities(No.BPHR202203081)the Fundamental Research Funds for Beijing Municipal Universities(No.X23025).
文摘Converting relational data into a property graph is advantageous for relational data analysis using graph algorithms.However,existing methods for constructing property graphs from relational data often require complex join operations when predefined entities and relationships are given.Additionally,constructing graphs from large-scale relational data is time-consuming due to the need to aggregate instances from multiple tables.To address this issue,this paper proposes a schema-based graph construction method called GraphCon.GraphCon employs a schema-based mapping mechanism to achieve equivalent mapping between the graph schema and the relational schema.Additionally,we optimize a complex join strategy,InstanceJoin,in the graph construction process.To improve efficiency in handling large-scale data,we introduce a parallel algorithm that includes a data partition strategy based on the graph schema and a load-balancing strategy to enhance scalability.Experiments using the TPC-H benchmark and real-life datasets validate the efficiency and scalability of our proposed methods.
