Pub Date : 2024-08-08DOI: 10.1109/TKDE.2024.3440654
Mang Ye;Yi Yu;Ziqin Shen;Wei Yu;Qingyan Zeng
The rising popularity of tabular data in data science applications has led to a surge of interest in utilizing deep neural networks (DNNs) to address tabular problems. Existing deep neural network methods are not effective in handling two fundamental challenges that are inherent in tabular data: permutation invariance (where the labels remain unchanged regardless of element order) and local dependency (where predictive labels are solely determined by local features). Furthermore, given the inherent heterogeneity among elements in tabular data, effectively capturing heterogeneous feature interactions remains unresolved. In this paper, we propose a novel Multiplex Cross-Feature Interaction Network (MPCFIN) by explicitly and systematically modeling feature relations with interactive graph neural networks. Specifically, MPCFIN first learns the most relevant features associated with individual features, and merges them to form cross-feature embedding. Subsequently, we design a multiplex graph neural network to learn enhanced representation for each sample. Comprehensive experiments on seven datasets demonstrate that MPCFIN exhibits superior performance over deep neural network methods in modeling the tabular data, showcasing consistent interpretability in its cross-feature embedding module for medical diagnosis applications.
{"title":"Cross-Feature Interactive Tabular Data Modeling With Multiplex Graph Neural Networks","authors":"Mang Ye;Yi Yu;Ziqin Shen;Wei Yu;Qingyan Zeng","doi":"10.1109/TKDE.2024.3440654","DOIUrl":"10.1109/TKDE.2024.3440654","url":null,"abstract":"The rising popularity of tabular data in data science applications has led to a surge of interest in utilizing deep neural networks (DNNs) to address tabular problems. Existing deep neural network methods are not effective in handling two fundamental challenges that are inherent in tabular data: permutation invariance (where the labels remain unchanged regardless of element order) and local dependency (where predictive labels are solely determined by local features). Furthermore, given the inherent heterogeneity among elements in tabular data, effectively capturing heterogeneous feature interactions remains unresolved. In this paper, we propose a novel Multiplex Cross-Feature Interaction Network (MPCFIN) by explicitly and systematically modeling feature relations with interactive graph neural networks. Specifically, MPCFIN first learns the most relevant features associated with individual features, and merges them to form cross-feature embedding. Subsequently, we design a multiplex graph neural network to learn enhanced representation for each sample. Comprehensive experiments on seven datasets demonstrate that MPCFIN exhibits superior performance over deep neural network methods in modeling the tabular data, showcasing consistent interpretability in its cross-feature embedding module for medical diagnosis applications.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7851-7864"},"PeriodicalIF":8.9,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federated Trajectory Matching (FTM) is gaining increasing importance in big trajectory data analytics, supporting diverse applications such as public health, law enforcement, and emergency response. FTM retrieves trajectories that match with a query trajectory from a large-scale trajectory database, while safeguarding the privacy of trajectories in both the query and the database. A naive solution to FTM is to process the query through Secure Multi-party Computation (SMC) across the entire database, which is inherently secure yet inevitably slow due to the massive secure operations. A promising acceleration strategy is to filter irrelevant trajectories from the database based on the query, thus reducing the SMC operations. However, a key challenge is how to publish the query in a way that both preserves privacy and enables efficient trajectory filtering. In this paper, we design ${sf GIST}$ , a novel framework for efficient Federated Trajectory Matching. ${sf GIST}$ is grounded in Geo-Indistinguishability, a privacy criterion dedicated to locations. It employs a new privacy mechanism for the query that facilitates efficient trajectory filtering. We theoretically prove the privacy guarantee of the mechanism and the accuracy of the filtering strategy of ${sf GIST}$ . Extensive evaluations on five real datasets show that ${sf GIST}$ is significantly faster and incurs up to 2 orders of magnitude lower communication cost than the state-of-the-arts.
{"title":"Efficient and Private Federated Trajectory Matching","authors":"Yuxiang Wang;Yuxiang Zeng;Shuyuan Li;Yuanyuan Zhang;Zimu Zhou;Yongxin Tong","doi":"10.1109/TKDE.2024.3424411","DOIUrl":"10.1109/TKDE.2024.3424411","url":null,"abstract":"Federated Trajectory Matching (FTM) is gaining increasing importance in big trajectory data analytics, supporting diverse applications such as public health, law enforcement, and emergency response. FTM retrieves trajectories that match with a query trajectory from a large-scale trajectory database, while safeguarding the privacy of trajectories in both the query and the database. A naive solution to FTM is to process the query through Secure Multi-party Computation (SMC) across the entire database, which is inherently secure yet inevitably slow due to the massive secure operations. A promising acceleration strategy is to filter irrelevant trajectories from the database based on the query, thus reducing the SMC operations. However, a key challenge is how to publish the query in a way that both preserves privacy and enables efficient trajectory filtering. In this paper, we design \u0000<inline-formula><tex-math>${sf GIST}$</tex-math></inline-formula>\u0000, a novel framework for efficient Federated Trajectory Matching. \u0000<inline-formula><tex-math>${sf GIST}$</tex-math></inline-formula>\u0000 is grounded in Geo-Indistinguishability, a privacy criterion dedicated to locations. It employs a new privacy mechanism for the query that facilitates efficient trajectory filtering. We theoretically prove the privacy guarantee of the mechanism and the accuracy of the filtering strategy of \u0000<inline-formula><tex-math>${sf GIST}$</tex-math></inline-formula>\u0000. Extensive evaluations on five real datasets show that \u0000<inline-formula><tex-math>${sf GIST}$</tex-math></inline-formula>\u0000 is significantly faster and incurs up to 2 orders of magnitude lower communication cost than the state-of-the-arts.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8079-8092"},"PeriodicalIF":8.9,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-07DOI: 10.1109/TKDE.2024.3437775
Chuang Zhao;Hongke Zhao;Xiaofang Zhou;Xiaomeng Li
Making accurate and safe clinical decisions for patients has long been a challenging task. With the proliferation of electronic health records and the rapid advancement of technology, drug recommender systems have emerged as invaluable aids for healthcare professionals, offering precise and secure prescriptions. Among prevailing methods, the exploration of motifs, defined as substructures with specific biological functions, has largely been overlooked. Nevertheless, the substantial impact of the motifs on drug efficacy and patient diseases implies that a more extensive incorporation could potentially improve the recommender systems. In light of this, we introduce DEPOT , an innovative drug recommendation framework developed from a motif-aware perspective. In our approach, we employ chemical decomposition to partition drug molecules into semantic motif-trees and design a structure-aware graph transformer to capture motif collaboration. This innovative practice preserves the topology knowledge and facilitates perception of drug functionality. To delve into the dynamic correlation between motifs and disease progression, we conduct a meticulous investigation from two perspectives: repetition and exploration. This comprehensive analysis allows us to gain valuable insights into the drug turnover, with the former focusing on reusability and the latter on discovering new requirements. We further formulate a historical weighting strategy for drug-drug interaction (DDI) objective, enabling adaptive control over the trade-off between accuracy and safety criteria throughout the training process. Extensive experiments conducted on four data sets validate the effectiveness and robustness of DEPOT .
{"title":"Enhancing Precision Drug Recommendations via In-Depth Exploration of Motif Relationships","authors":"Chuang Zhao;Hongke Zhao;Xiaofang Zhou;Xiaomeng Li","doi":"10.1109/TKDE.2024.3437775","DOIUrl":"10.1109/TKDE.2024.3437775","url":null,"abstract":"Making accurate and safe clinical decisions for patients has long been a challenging task. With the proliferation of electronic health records and the rapid advancement of technology, drug recommender systems have emerged as invaluable aids for healthcare professionals, offering precise and secure prescriptions. Among prevailing methods, the exploration of motifs, defined as substructures with specific biological functions, has largely been overlooked. Nevertheless, the substantial impact of the motifs on drug efficacy and patient diseases implies that a more extensive incorporation could potentially improve the recommender systems. In light of this, we introduce \u0000<italic>DEPOT</i>\u0000, an innovative drug recommendation framework developed from a motif-aware perspective. In our approach, we employ chemical decomposition to partition drug molecules into semantic motif-trees and design a structure-aware graph transformer to capture motif collaboration. This innovative practice preserves the topology knowledge and facilitates perception of drug functionality. To delve into the dynamic correlation between motifs and disease progression, we conduct a meticulous investigation from two perspectives: repetition and exploration. This comprehensive analysis allows us to gain valuable insights into the drug turnover, with the former focusing on reusability and the latter on discovering new requirements. We further formulate a historical weighting strategy for drug-drug interaction (DDI) objective, enabling adaptive control over the trade-off between accuracy and safety criteria throughout the training process. Extensive experiments conducted on four data sets validate the effectiveness and robustness of \u0000<italic>DEPOT</i>\u0000.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8164-8178"},"PeriodicalIF":8.9,"publicationDate":"2024-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141969044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1109/TKDE.2024.3438259
Guoliang He;Dawei Jin;Lifang Dai;Xin Xin;Zhiwen Yu;C. L. Philip Chen
Recently, rule-based classification on multivariate time series (MTS) data has gained lots of attention, which could improve the interpretability of classification. However, state-of-the-art approaches suffer from three major issues. 1) few existing studies consider temporal relations among features in a rule, which could not adequately express the essential characteristics of MTS data. 2) due to the concept drift and time warping of MTS data, traditional methods could not mine essential characteristics of MTS data. 3) existing online learning algorithms could not effectively update shapelet-based temporal association rules of MTS data due to its temporal relationships among features of different variables. To handle these issues, we propose an online learning method for temporal association rule on dynamically collected MTS data (OTARL). First, a new type of rule named temporal association rule is defined and mined to represent temporal relationships among features in a rule. Second, an online learning mechanism with a probability correlation-based evaluation criterion is proposed to realize the online learning of temporal association rules on dynamically collected MTS data. Finally, an ensemble classification approach based on maximum-likelihood estimation is advanced to further enhance the classification performance. We conduct experiments on ten real-world datasets to verify the effectiveness and efficiency of our approach.
{"title":"Online Learning of Temporal Association Rule on Dynamic Multivariate Time Series Data","authors":"Guoliang He;Dawei Jin;Lifang Dai;Xin Xin;Zhiwen Yu;C. L. Philip Chen","doi":"10.1109/TKDE.2024.3438259","DOIUrl":"10.1109/TKDE.2024.3438259","url":null,"abstract":"Recently, rule-based classification on multivariate time series (MTS) data has gained lots of attention, which could improve the interpretability of classification. However, state-of-the-art approaches suffer from three major issues. 1) few existing studies consider temporal relations among features in a rule, which could not adequately express the essential characteristics of MTS data. 2) due to the concept drift and time warping of MTS data, traditional methods could not mine essential characteristics of MTS data. 3) existing online learning algorithms could not effectively update shapelet-based temporal association rules of MTS data due to its temporal relationships among features of different variables. To handle these issues, we propose an online learning method for temporal association rule on dynamically collected MTS data (OTARL). First, a new type of rule named temporal association rule is defined and mined to represent temporal relationships among features in a rule. Second, an online learning mechanism with a probability correlation-based evaluation criterion is proposed to realize the online learning of temporal association rules on dynamically collected MTS data. Finally, an ensemble classification approach based on maximum-likelihood estimation is advanced to further enhance the classification performance. We conduct experiments on ten real-world datasets to verify the effectiveness and efficiency of our approach.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8954-8966"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shapley value provides a unique way to fairly assess each player's contribution in a coalition and has enjoyed many applications. However, the exact computation of Shapley value is #P-hard due to the combinatoric nature of Shapley value. Many existing applications of Shapley value are based on Monte-Carlo approximation, which requires a large number of samples and the assessment of utility on many coalitions to reach high-quality approximation, and thus is still far from being efficient. Can we achieve an efficient approximation of Shapley value by smartly obtaining samples? In this paper, we treat the sampling approach to Shapley value approximation as a stratified sampling problem. Our main technical contributions are a novel stratification design and a sampling method based on Neyman allocation. Moreover, computing the Shapley value in a dynamic setting, where new players may join the game and others may leave it poses an additional challenge due to the considerable cost of recomputing from scratch. To tackle this issue, we propose to capture changes in Shapley value, making our approaches applicable to scenarios with dynamic players. Experimental results on several real data sets and synthetic data sets demonstrate the effectiveness and efficiency of our approaches.
{"title":"Shapley Value Approximation Based on Complementary Contribution","authors":"Qiheng Sun;Jiayao Zhang;Jinfei Liu;Li Xiong;Jian Pei;Kui Ren","doi":"10.1109/TKDE.2024.3438213","DOIUrl":"10.1109/TKDE.2024.3438213","url":null,"abstract":"Shapley value provides a unique way to fairly assess each player's contribution in a coalition and has enjoyed many applications. However, the exact computation of Shapley value is #P-hard due to the combinatoric nature of Shapley value. Many existing applications of Shapley value are based on Monte-Carlo approximation, which requires a large number of samples and the assessment of utility on many coalitions to reach high-quality approximation, and thus is still far from being efficient. Can we achieve an efficient approximation of Shapley value by smartly obtaining samples? In this paper, we treat the sampling approach to Shapley value approximation as a stratified sampling problem. Our main technical contributions are a novel stratification design and a sampling method based on Neyman allocation. Moreover, computing the Shapley value in a dynamic setting, where new players may join the game and others may leave it poses an additional challenge due to the considerable cost of recomputing from scratch. To tackle this issue, we propose to capture changes in Shapley value, making our approaches applicable to scenarios with dynamic players. Experimental results on several real data sets and synthetic data sets demonstrate the effectiveness and efficiency of our approaches.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9263-9281"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1109/TKDE.2024.3438074
Seonghak Kim;Gyeongdo Ham;Yucheol Cho;Daeshik Kim
The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model). However, most existing KD techniques rely on Kullback-Leibler (KL) divergence, which has certain limitations. First, if the teacher distribution has high entropy, the KL divergence's mode-averaging nature hinders the transfer of sufficient target information. Second, when the teacher distribution has low entropy, the KL divergence tends to excessively focus on specific modes, which fails to convey an abundant amount of valuable knowledge to the student. Consequently, when dealing with datasets that contain numerous confounding or challenging samples, student models may struggle to acquire sufficient knowledge, resulting in subpar performance. Furthermore, in previous KD approaches, we observed that data augmentation, a technique aimed at enhancing a model's generalization, can have an adverse impact. Therefore, we propose a Robustness-Reinforced Knowledge Distillation (R2KD) that leverages correlation distance and network pruning. This approach enables KD to effectively incorporate data augmentation for performance improvement. Extensive experiments on various datasets, including CIFAR-100, FGVR, TinyImagenet, and ImageNet, demonstrate our method's superiority over current state-of-the-art methods.
{"title":"Robustness-Reinforced Knowledge Distillation With Correlation Distance and Network Pruning","authors":"Seonghak Kim;Gyeongdo Ham;Yucheol Cho;Daeshik Kim","doi":"10.1109/TKDE.2024.3438074","DOIUrl":"10.1109/TKDE.2024.3438074","url":null,"abstract":"The improvement in the performance of efficient and lightweight models (i.e., the student model) is achieved through knowledge distillation (KD), which involves transferring knowledge from more complex models (i.e., the teacher model). However, most existing KD techniques rely on Kullback-Leibler (KL) divergence, which has certain limitations. First, if the teacher distribution has high entropy, the KL divergence's mode-averaging nature hinders the transfer of sufficient target information. Second, when the teacher distribution has low entropy, the KL divergence tends to excessively focus on specific modes, which fails to convey an abundant amount of valuable knowledge to the student. Consequently, when dealing with datasets that contain numerous confounding or challenging samples, student models may struggle to acquire sufficient knowledge, resulting in subpar performance. Furthermore, in previous KD approaches, we observed that data augmentation, a technique aimed at enhancing a model's generalization, can have an adverse impact. Therefore, we propose a Robustness-Reinforced Knowledge Distillation (R2KD) that leverages correlation distance and network pruning. This approach enables KD to effectively incorporate data augmentation for performance improvement. Extensive experiments on various datasets, including CIFAR-100, FGVR, TinyImagenet, and ImageNet, demonstrate our method's superiority over current state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9163-9175"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Graph learning methods have achieved remarkable performance in various domains such as social recommendation, financial fraud detection, and so on. In real applications, the underlying graph is often dynamically evolving and thus, some recent studies focus on integrating the temporal topology information of graphs into the GNN for learning graph embedding. However, the robustness of training GNNs for dynamic graphs has not been discussed so far. The major reason is how to attack dynamic graph embedding still remains largely untouched, let alone how to defend against the attacks. To enable robust training of GNNs for dynamic graphs, in this paper, we investigate the problem of how to generate attacks and defend against attacks for dynamic graph embedding. Attacking dynamic graph embedding is more challenging than attacking static graph embedding as we need to understand the temporal dynamics of graphs as well as its impact on the embedding and the injected perturbations should be distinguished from the natural evolution. In addition, the defense is very challenging as the perturbations may be hidden within the natural evolution. To tackle these technical challenges, in this paper, we first develop a novel gradient-based attack method from an optimization perspective to generate perturbations to fool dynamic graph learning methods, where a key idea is to use gradient dynamics to attack the natural dynamics of the graph. Further, we borrow the idea of the attack method and integrate it with adversarial training to train a more robust dynamic graph learning method to defend against hand-crafted attacks. Finally, extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed attack and defense method, where our defense method not only achieves comparable performance on clean graphs but also significantly increases the defense performance on attacked graphs.
{"title":"Adversarial Attack and Defense on Discrete Time Dynamic Graphs","authors":"Ziwei Zhao;Yu Yang;Zikai Yin;Tong Xu;Xi Zhu;Fake Lin;Xueying Li;Enhong Chen","doi":"10.1109/TKDE.2024.3438238","DOIUrl":"10.1109/TKDE.2024.3438238","url":null,"abstract":"Graph learning methods have achieved remarkable performance in various domains such as social recommendation, financial fraud detection, and so on. In real applications, the underlying graph is often dynamically evolving and thus, some recent studies focus on integrating the temporal topology information of graphs into the GNN for learning graph embedding. However, the robustness of training GNNs for dynamic graphs has not been discussed so far. The major reason is how to attack dynamic graph embedding still remains largely untouched, let alone how to defend against the attacks. To enable robust training of GNNs for dynamic graphs, in this paper, we investigate the problem of how to generate attacks and defend against attacks for dynamic graph embedding. Attacking dynamic graph embedding is more challenging than attacking static graph embedding as we need to understand the temporal dynamics of graphs as well as its impact on the embedding and the injected perturbations should be distinguished from the natural evolution. In addition, the defense is very challenging as the perturbations may be hidden within the natural evolution. To tackle these technical challenges, in this paper, we first develop a novel gradient-based attack method from an optimization perspective to generate perturbations to fool dynamic graph learning methods, where a key idea is to use gradient dynamics to attack the natural dynamics of the graph. Further, we borrow the idea of the attack method and integrate it with adversarial training to train a more robust dynamic graph learning method to defend against hand-crafted attacks. Finally, extensive experiments on two real-world datasets demonstrate the effectiveness of the proposed attack and defense method, where our defense method not only achieves comparable performance on clean graphs but also significantly increases the defense performance on attacked graphs.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"7600-7611"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The goal of mixed-modality clustering, which differs from typical multi-modality/view clustering, is to divide samples derived from various modalities into several clusters. This task has to solve two critical semantic gap problems: i) how to generate the missing modalities without the pairwise-modality data; and ii) how to align the representations of heterogeneous modalities. To tackle the above problems, this paper proposes a novel mixed-modality clustering model, which integrates the missing-modality generation and the heterogeneous modality alignment into a unified framework. During the missing-modality generation process, a bidirectional mapping is established between different modalities, enabling generation of preliminary representations for the missing-modality using information from another modality. Then the intra-modality bipartite graphs are constructed to help generate better missing-modality representations by weighted aggregating existing intra-modality neighbors. In this way, a pairwise-modality representation for each sample can be obtained. In the process of heterogeneous modality alignment, each modality is modelled as a graph to capture the global structure among intra-modality samples and is aligned against the heterogeneous modality representations through the adaptive heterogeneous graph matching module. Experimental results on three public datasets show the effectiveness of the proposed model compared to multiple state-of-the-art multi-modality/view clustering methods.
{"title":"Mixed-Modality Clustering via Generative Graph Structure Matching","authors":"Xiaxia He;Boyue Wang;Junbin Gao;Qianqian Wang;Yongli Hu;Baocai Yin","doi":"10.1109/TKDE.2024.3434556","DOIUrl":"10.1109/TKDE.2024.3434556","url":null,"abstract":"The goal of mixed-modality clustering, which differs from typical multi-modality/view clustering, is to divide samples derived from various modalities into several clusters. This task has to solve two critical semantic gap problems: i) how to generate the missing modalities without the pairwise-modality data; and ii) how to align the representations of heterogeneous modalities. To tackle the above problems, this paper proposes a novel mixed-modality clustering model, which integrates the missing-modality generation and the heterogeneous modality alignment into a unified framework. During the missing-modality generation process, a bidirectional mapping is established between different modalities, enabling generation of preliminary representations for the missing-modality using information from another modality. Then the intra-modality bipartite graphs are constructed to help generate better missing-modality representations by weighted aggregating existing intra-modality neighbors. In this way, a pairwise-modality representation for each sample can be obtained. In the process of heterogeneous modality alignment, each modality is modelled as a graph to capture the global structure among intra-modality samples and is aligned against the heterogeneous modality representations through the adaptive heterogeneous graph matching module. Experimental results on three public datasets show the effectiveness of the proposed model compared to multiple state-of-the-art multi-modality/view clustering methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8773-8786"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10623373","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141969014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-05DOI: 10.1109/TKDE.2024.3438274
Yan Li;Chenyu Ma;Rong Gao;Youxi Wu;Jinyan Li;Wenjian Wang;Xindong Wu
Order-preserving pattern (OPP) mining is a type of sequential pattern mining method in which a group of ranks of time series is used to represent an OPP. This approach can discover frequent trends in time series. Existing OPP mining algorithms consider data points at different time to be equally important; however, newer data usually have a more significant impact, while older data have a weaker impact. We therefore introduce the forgetting mechanism into OPP mining to reduce the importance of older data. This paper explores the mining of OPPs with forgetting mechanism (OPF) and proposes an algorithm called OPF-Miner that can discover frequent OPFs. OPF-Miner performs two tasks, candidate pattern generation and support calculation. In candidate pattern generation, OPF-Miner employs a maximal support priority strategy and a group pattern fusion strategy to avoid redundant pattern fusions. For support calculation, we propose an algorithm called support calculation with forgetting mechanism, which uses prefix and suffix pattern pruning strategies to avoid redundant support calculations. The experiments are conducted on nine datasets and 12 alternative algorithms. The results verify that OPF-Miner is superior to other competitive algorithms. More importantly, OPF-Miner yields good clustering performance for time series, since the forgetting mechanism is employed.
保序模式（OPP）挖掘是一种序列模式挖掘方法，其中使用一组时间序列的等级来表示 OPP。这种方法可以发现时间序列中的频繁趋势。现有的 OPP 挖掘算法认为不同时间的数据点同等重要；但是，较新的数据通常影响更大，而较老的数据影响较弱。因此，我们在 OPP 挖掘中引入了遗忘机制，以降低旧数据的重要性。本文探讨了带有遗忘机制（OPF）的OPP挖掘，并提出了一种名为OPF-Miner的算法，可以发现频繁的OPF。OPF-Miner 执行两项任务：候选模式生成和支持计算。在候选模式生成中，OPF-Miner 采用了最大支持优先策略和分组模式融合策略，以避免冗余模式融合。在支持计算方面，我们提出了一种名为 "带遗忘机制的支持计算 "的算法，它使用前缀和后缀模式剪枝策略来避免冗余支持计算。我们在 9 个数据集和 12 种备选算法上进行了实验。结果验证了 OPF-Miner 优于其他竞争算法。更重要的是，由于采用了遗忘机制，OPF-Miner 对时间序列具有良好的聚类性能。
{"title":"OPF-Miner: Order-Preserving Pattern Mining With Forgetting Mechanism for Time Series","authors":"Yan Li;Chenyu Ma;Rong Gao;Youxi Wu;Jinyan Li;Wenjian Wang;Xindong Wu","doi":"10.1109/TKDE.2024.3438274","DOIUrl":"10.1109/TKDE.2024.3438274","url":null,"abstract":"Order-preserving pattern (OPP) mining is a type of sequential pattern mining method in which a group of ranks of time series is used to represent an OPP. This approach can discover frequent trends in time series. Existing OPP mining algorithms consider data points at different time to be equally important; however, newer data usually have a more significant impact, while older data have a weaker impact. We therefore introduce the forgetting mechanism into OPP mining to reduce the importance of older data. This paper explores the mining of OPPs with forgetting mechanism (OPF) and proposes an algorithm called OPF-Miner that can discover frequent OPFs. OPF-Miner performs two tasks, candidate pattern generation and support calculation. In candidate pattern generation, OPF-Miner employs a maximal support priority strategy and a group pattern fusion strategy to avoid redundant pattern fusions. For support calculation, we propose an algorithm called support calculation with forgetting mechanism, which uses prefix and suffix pattern pruning strategies to avoid redundant support calculations. The experiments are conducted on nine datasets and 12 alternative algorithms. The results verify that OPF-Miner is superior to other competitive algorithms. More importantly, OPF-Miner yields good clustering performance for time series, since the forgetting mechanism is employed.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"8981-8995"},"PeriodicalIF":8.9,"publicationDate":"2024-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141935926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-08-02DOI: 10.1109/TKDE.2024.3437243
Zi Chen;Xinyu Ji;Long Yuan;Xuemin Lin;Wenjie Zhang;Shan Huang
Shortest path query on road networks is a fundamental problem to support many location-based services and wide variant applications. Contraction Hierarchies(CH) is widely adopted to accelerate the shortest path query by leveraging shortcuts among vertices. However, the state-of-the-art CH construction method named $mathsf{VCHCons}$ suffers from inefficiencies due to their strong reliance on pre-determined vertex order. This leads to the generation of a large number of invalid shortcuts and the limit of parallel processing capability. Motivated by it, in this paper, an innovative CH construction algorithm called $mathsf{ECHCons}$ is devised following an edge-centric paradigm, which addresses the issue of invalid shortcut production by introducing a novel edge-ordering strategy. Furthermore, it optimizes shortcut calculation within a dynamically constructed optimal subgraph, which is significantly smaller than the original network, thus shrinking the traversal space during index construction. To further enhance efficiency and overcome the limitations in parallelism inherent to $mathsf{VCHCons}$ , our approach leverages batch contraction of edges and introduces a well-defined lower bound technique to unlock more efficient parallel computation resources. Our approach provides both theoretical guarantee and practical advancement in CH construction. Extensive and comprehensive experiments are conducted on real road networks. The experimental results demonstrate the effectiveness and efficiency of our proposed approach.
{"title":"Parallel Contraction Hierarchies Construction on Road Networks","authors":"Zi Chen;Xinyu Ji;Long Yuan;Xuemin Lin;Wenjie Zhang;Shan Huang","doi":"10.1109/TKDE.2024.3437243","DOIUrl":"10.1109/TKDE.2024.3437243","url":null,"abstract":"Shortest path query on road networks is a fundamental problem to support many location-based services and wide variant applications. Contraction Hierarchies(CH) is widely adopted to accelerate the shortest path query by leveraging shortcuts among vertices. However, the state-of-the-art CH construction method named \u0000<inline-formula><tex-math>$mathsf{VCHCons}$</tex-math></inline-formula>\u0000 suffers from inefficiencies due to their strong reliance on pre-determined vertex order. This leads to the generation of a large number of invalid shortcuts and the limit of parallel processing capability. Motivated by it, in this paper, an innovative CH construction algorithm called \u0000<inline-formula><tex-math>$mathsf{ECHCons}$</tex-math></inline-formula>\u0000 is devised following an edge-centric paradigm, which addresses the issue of invalid shortcut production by introducing a novel edge-ordering strategy. Furthermore, it optimizes shortcut calculation within a dynamically constructed optimal subgraph, which is significantly smaller than the original network, thus shrinking the traversal space during index construction. To further enhance efficiency and overcome the limitations in parallelism inherent to \u0000<inline-formula><tex-math>$mathsf{VCHCons}$</tex-math></inline-formula>\u0000, our approach leverages batch contraction of edges and introduces a well-defined lower bound technique to unlock more efficient parallel computation resources. Our approach provides both theoretical guarantee and practical advancement in CH construction. Extensive and comprehensive experiments are conducted on real road networks. The experimental results demonstrate the effectiveness and efficiency of our proposed approach.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"36 12","pages":"9011-9024"},"PeriodicalIF":8.9,"publicationDate":"2024-08-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141883009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：