Pub Date : 2024-12-24DOI: 10.1109/TNSE.2024.3511059
Dusit Tao Niyato
As The incoming Editor-in-Chief of IEEE Transactions on Network Science and Engineering (TNSE), I extend my deepest gratitude to the IEEE Communications Society, the search committee members, and the TNSE community for entrusting me with this significant role. In today's fast-evolving and multidisciplinary publishing environment, the outgoing EiC, Prof. Jianwei Huang, has steered TNSE with remarkable dedication, fostering its growth and maintaining the journal's reputation for excellence. On behalf of the entire TNSE community—including readers, authors, reviewers, editors, and support staff—I sincerely thank Prof. Jianwei Huang for their outstanding contributions and leadership over the past years.
{"title":"Editorial: Introduction of New EiC","authors":"Dusit Tao Niyato","doi":"10.1109/TNSE.2024.3511059","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3511059","url":null,"abstract":"As The incoming Editor-in-Chief of \u0000<sc>IEEE Transactions on Network Science and Engineering</small>\u0000 (TNSE), I extend my deepest gratitude to the IEEE Communications Society, the search committee members, and the TNSE community for entrusting me with this significant role. In today's fast-evolving and multidisciplinary publishing environment, the outgoing EiC, Prof. Jianwei Huang, has steered TNSE with remarkable dedication, fostering its growth and maintaining the journal's reputation for excellence. On behalf of the entire TNSE community—including readers, authors, reviewers, editors, and support staff—I sincerely thank Prof. Jianwei Huang for their outstanding contributions and leadership over the past years.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"3-3"},"PeriodicalIF":6.7,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10814997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890338","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 : 2024-12-24DOI: 10.1109/TNSE.2024.3514032
Jianwei Huang
As the Editor-in-Chief of the IEEE Transactions on Network Science and Engineering (TNSE) from 2021 to 2024, it is my distinct pleasure to reflect on the tremendous progress we have made over the past four years. Together, as a vibrant community of researchers, reviewers, and editors, we have consistently endeavored to push the boundaries of network science and engineering. I would like to extend heartfelt gratitude to those who have made this success possible.
{"title":"Editorial: IEEE Transactions on Network Science and Engineering 2025 New Year Editorial","authors":"Jianwei Huang","doi":"10.1109/TNSE.2024.3514032","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3514032","url":null,"abstract":"As the Editor-in-Chief of the \u0000<sc>IEEE Transactions on Network Science and Engineering</small>\u0000 (TNSE) from 2021 to 2024, it is my distinct pleasure to reflect on the tremendous progress we have made over the past four years. Together, as a vibrant community of researchers, reviewers, and editors, we have consistently endeavored to push the boundaries of network science and engineering. I would like to extend heartfelt gratitude to those who have made this success possible.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"1-2"},"PeriodicalIF":6.7,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10814998","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142890368","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 : 2024-12-18DOI: 10.1109/TNSE.2024.3520100
{"title":"2024 Index IEEE Transactions on Network Science and Engineering Vol. 11","authors":"","doi":"10.1109/TNSE.2024.3520100","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3520100","url":null,"abstract":"","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"11 6","pages":"6718-6822"},"PeriodicalIF":6.7,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10807093","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844378","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 : 2024-12-09DOI: 10.1109/TNSE.2024.3513456
Xiaoyu Zhang;Wenchuan Yang;Jiawei Feng;Bitao Dai;Tianci Bu;Xin Lu
Identifying structures in common forms the basis for networked systems design and optimization. However, real structures represented by graphs are often of varying sizes, leading to the low accuracy of traditional graph classification methods. These graphs are called cross-scale graphs. To overcome this limitation, in this study, we propose GSpect, an advanced spectral graph filtering model for cross-scale graph classification tasks. Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations. We design a spectral-pooling layer which aggregates nodes to one node to reduce the cross-scale graphs to the same size. We collect and construct the cross-scale benchmark data set, MSG (Multi Scale Graphs). Experiments reveal that, on open data sets, GSpect improves the performance of classification accuracy by 1.62% on average, and for a maximum of 3.33% on PROTEINS. On MSG, GSpect improves the performance of classification accuracy by 13.38% on average. GSpect fills the gap in cross-scale graph classification studies and has potential to provide assistance in application research like diagnosis of brain disease by predicting the brain network's label and developing new drugs with molecular structures learned from their counterparts in other systems.
{"title":"GSpect: Spectral Filtering for Cross-Scale Graph Classification","authors":"Xiaoyu Zhang;Wenchuan Yang;Jiawei Feng;Bitao Dai;Tianci Bu;Xin Lu","doi":"10.1109/TNSE.2024.3513456","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3513456","url":null,"abstract":"Identifying structures in common forms the basis for networked systems design and optimization. However, real structures represented by graphs are often of varying sizes, leading to the low accuracy of traditional graph classification methods. These graphs are called cross-scale graphs. To overcome this limitation, in this study, we propose GSpect, an advanced spectral graph filtering model for cross-scale graph classification tasks. Compared with other methods, we use graph wavelet neural networks for the convolution layer of the model, which aggregates multi-scale messages to generate graph representations. We design a spectral-pooling layer which aggregates nodes to one node to reduce the cross-scale graphs to the same size. We collect and construct the cross-scale benchmark data set, MSG (Multi Scale Graphs). Experiments reveal that, on open data sets, GSpect improves the performance of classification accuracy by 1.62% on average, and for a maximum of 3.33% on PROTEINS. On MSG, GSpect improves the performance of classification accuracy by 13.38% on average. GSpect fills the gap in cross-scale graph classification studies and has potential to provide assistance in application research like diagnosis of brain disease by predicting the brain network's label and developing new drugs with molecular structures learned from their counterparts in other systems.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"547-558"},"PeriodicalIF":6.7,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880326","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 : 2024-11-28DOI: 10.1109/TNSE.2024.3498942
Qihui Zhu;Shenwen Chen;Jingbin Zhang;Gang Yan;Wenbo Du
Controlling the dynamics of complex networks with only a few driver nodes is a significant objective for system control. However, the energy required for control becomes prohibitively large when the fraction of driver nodes is small. Previous methods to reduce control energy have mainly focused on increasing the number or altering the placement of driver nodes. In this paper, a novel approach is proposed to reduce control energy by rewiring networks while keeping the number of driver nodes unchanged. We model network rewiring to an optimization problem and develop a memetic algorithm to solve it accurately and efficiently. Specifically, we introduce a connectivity-preserving crossover operator to avoid searching in invalid solution space and design a local search operator to accelerate the convergence of the algorithm according to the network heterogeneity. Experimental results on both synthetic networks and real networks demonstrate the effectiveness of the proposed approach. Notably, our findings reveal that networks with low control energy tend to exhibit a âcore-chainâ structure, where control nodes and high-weight edges form a densely connected core, while other nodes and edges form independent chains connected to the core's boundaries. We further analyze the statistical description and formation mechanism of this structure.
{"title":"Network Topology Optimization for Energy-Efficient Control","authors":"Qihui Zhu;Shenwen Chen;Jingbin Zhang;Gang Yan;Wenbo Du","doi":"10.1109/TNSE.2024.3498942","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3498942","url":null,"abstract":"Controlling the dynamics of complex networks with only a few driver nodes is a significant objective for system control. However, the energy required for control becomes prohibitively large when the fraction of driver nodes is small. Previous methods to reduce control energy have mainly focused on increasing the number or altering the placement of driver nodes. In this paper, a novel approach is proposed to reduce control energy by rewiring networks while keeping the number of driver nodes unchanged. We model network rewiring to an optimization problem and develop a memetic algorithm to solve it accurately and efficiently. Specifically, we introduce a connectivity-preserving crossover operator to avoid searching in invalid solution space and design a local search operator to accelerate the convergence of the algorithm according to the network heterogeneity. Experimental results on both synthetic networks and real networks demonstrate the effectiveness of the proposed approach. Notably, our findings reveal that networks with low control energy tend to exhibit a âcore-chainâ structure, where control nodes and high-weight edges form a densely connected core, while other nodes and edges form independent chains connected to the core's boundaries. We further analyze the statistical description and formation mechanism of this structure.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"423-432"},"PeriodicalIF":6.7,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880410","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}
In this paper, we investigate the distributed robust state estimation of non-Gaussian systems under unknown deception attacks with the imprecise constraint information. Leveraging the advantage of multi-kernel maximum correntropy criterion (MK-MCC) in non-Gaussian signal processing, a novel maximum-a-posterior like utility function (MAP-LUF) is designed inspired by the traditional 2-norm form cost function, where the inaccurate constraint information is taken into consideration. The direct solution of MAP-LUF gives rise to the centralized MK-MCC based state-constrained Kalman filter (C-MKMCSCKF) through fixed point iteration. Subsequently, the corresponding distributed algorithm is obtained by incorporating the consensus average in the computation of sum terms existing in the C-MKMCSCKF algorithm, which enables local information sharing to approximate the centralized estimation accuracy. Furthermore, we also establish the connection between the proposed centralized algorithm and the Banach theorem through dimension extension, and provide the convergence condition. The effectiveness of our proposed algorithms is validated through comparisons with related works in typical target tracking scenarios over sensor network.
{"title":"Distributed Multi-Kernel Maximum Correntropy State-Constrained Kalman Filter Under Deception Attacks","authors":"Guoqing Wang;Zhaolei Zhu;Chunyu Yang;Lei Ma;Wei Dai;Xinkai Chen","doi":"10.1109/TNSE.2024.3506553","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3506553","url":null,"abstract":"In this paper, we investigate the distributed robust state estimation of non-Gaussian systems under unknown deception attacks with the imprecise constraint information. Leveraging the advantage of multi-kernel maximum correntropy criterion (MK-MCC) in non-Gaussian signal processing, a novel maximum-a-posterior like utility function (MAP-LUF) is designed inspired by the traditional 2-norm form cost function, where the inaccurate constraint information is taken into consideration. The direct solution of MAP-LUF gives rise to the centralized MK-MCC based state-constrained Kalman filter (C-MKMCSCKF) through fixed point iteration. Subsequently, the corresponding distributed algorithm is obtained by incorporating the consensus average in the computation of sum terms existing in the C-MKMCSCKF algorithm, which enables local information sharing to approximate the centralized estimation accuracy. Furthermore, we also establish the connection between the proposed centralized algorithm and the Banach theorem through dimension extension, and provide the convergence condition. The effectiveness of our proposed algorithms is validated through comparisons with related works in typical target tracking scenarios over sensor network.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"533-546"},"PeriodicalIF":6.7,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880332","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}
Link prediction is a classical problem in graph analysis with many practical applications. For directed graphs, recently developed deep learning approaches typically analyze node similarities through contrastive learning and aggregate neighborhood information through graph convolutions. In this work, we propose a novel graph neural network (GNN) framework to fuse feature embedding with community information. We theoretically demonstrate that such hybrid features can improve the performance of directed link prediction. To utilize such features efficiently, we also propose an approach to transform input graphs into directed line graphs so that nodes in the transformed graph can aggregate more information during graph convolutions. Experiments on benchmark datasets show that our approach outperforms the state-of-the-art in most cases when 30%, 40%, 50%, and 60% of the connected links are used as training data, respectively.
{"title":"Directed Link Prediction Using GNN With Local and Global Feature Fusion","authors":"Yuyang Zhang;Xu Shen;Yu Xie;Ka-Chun Wong;Weidun Xie;Chengbin Peng","doi":"10.1109/TNSE.2024.3498434","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3498434","url":null,"abstract":"Link prediction is a classical problem in graph analysis with many practical applications. For directed graphs, recently developed deep learning approaches typically analyze node similarities through contrastive learning and aggregate neighborhood information through graph convolutions. In this work, we propose a novel graph neural network (GNN) framework to fuse feature embedding with community information. We theoretically demonstrate that such hybrid features can improve the performance of directed link prediction. To utilize such features efficiently, we also propose an approach to transform input graphs into directed line graphs so that nodes in the transformed graph can aggregate more information during graph convolutions. Experiments on benchmark datasets show that our approach outperforms the state-of-the-art in most cases when 30%, 40%, 50%, and 60% of the connected links are used as training data, respectively.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"409-422"},"PeriodicalIF":6.7,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880329","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 : 2024-11-21DOI: 10.1109/TNSE.2024.3503666
Ayesha Siddiqa;Junho Seo;Malik Muhammad Saad;Dongkyun Kim
Future wireless networks are expected to achieve uniform quality of service (QoS) and seamless connectivity across vast coverage areas. Cell-free (CF) massive multiple-input, multiple-output (mMIMO) networks emerge as a promising solution to achieve these goals by minimizing signal interference and enhancing network performance. However, the existing research contributions in CF mMIMO networks face significant challenges related to signal overhead, network load, and computation complexity on the fronthaul, resulting in unscalability. Considering these limitations, we propose a novel space division multiple access (SDMA)-based network virtualization (SNV) scheme to maximize the uplink/downlink spectral efficiency in the Internet of Things (IoT)-enabled CF mMIMO networks. Our system architecture leverages multiple IoT-enabled wireless access points (APs) equipped with various antennas, establishing independent communication links to serve user equipment (UEs) simultaneously. The integration of stream-based encoding and minimum mean square error estimation enables UEs to receive accurate data, improve channel capacity, and minimize the computation complexity on fronthaul. Our extensive simulation results demonstrate that the proposed scheme significantly outperforms current state-of-the-art schemes while ensuring scalability for CF mMIMO networks.
{"title":"Optimizing Spectral Efficiency: An SNV Scheme for IoT-Enabled CF mMIMO Networks","authors":"Ayesha Siddiqa;Junho Seo;Malik Muhammad Saad;Dongkyun Kim","doi":"10.1109/TNSE.2024.3503666","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3503666","url":null,"abstract":"Future wireless networks are expected to achieve uniform quality of service (QoS) and seamless connectivity across vast coverage areas. Cell-free (CF) massive multiple-input, multiple-output (mMIMO) networks emerge as a promising solution to achieve these goals by minimizing signal interference and enhancing network performance. However, the existing research contributions in CF mMIMO networks face significant challenges related to signal overhead, network load, and computation complexity on the fronthaul, resulting in unscalability. Considering these limitations, we propose a novel space division multiple access (SDMA)-based network virtualization (SNV) scheme to maximize the uplink/downlink spectral efficiency in the Internet of Things (IoT)-enabled CF mMIMO networks. Our system architecture leverages multiple IoT-enabled wireless access points (APs) equipped with various antennas, establishing independent communication links to serve user equipment (UEs) simultaneously. The integration of stream-based encoding and minimum mean square error estimation enables UEs to receive accurate data, improve channel capacity, and minimize the computation complexity on fronthaul. Our extensive simulation results demonstrate that the proposed scheme significantly outperforms current state-of-the-art schemes while ensuring scalability for CF mMIMO networks.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"488-504"},"PeriodicalIF":6.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880337","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 : 2024-11-21DOI: 10.1109/TNSE.2024.3503904
Guoju Gao;Zhaorong Qian;He Huang;Yu-E Sun;Yang Du
Accurate and fast per-flow size traffic measurement is fundamental to some network applications, especially in face of the processing and memory constraints of switches. Sketch, a compact data structure, can output high-fidelity approximate per-flow statistics. However, most existing sketches, such as Count-Min, are trapped in the dilemma between a large counting range and memory waste, due to the highly skewed characteristics of network traffic size distribution. In this paper, we propose an adaptive counter-splicing-based sketch for per-flow size measurement, called TailoredSketch. Specifically, we divide each counter of TailoredSketch into two parts, named basic and carry-in counters. When the basic counters overflow, the carry-in counters work, and meanwhile several carry-in counters in different positions can be spliced to expand the counting range. We also incorporate sampling into TailoredSketch, where we set different sampling probabilities at each layer to distinguish between elephant and mouse flows better. In order to further increase the memory utilization of TailoredSketch, we optimize it by removing the flag bits of each counter. Extensive experiments based on the real-world dataset CAIDA show that our sketch can achieve better overall performance compared to several existing algorithms.
{"title":"TailoredSketch: A Fast and Adaptive Sketch for Efficient Per-Flow Size Measurement","authors":"Guoju Gao;Zhaorong Qian;He Huang;Yu-E Sun;Yang Du","doi":"10.1109/TNSE.2024.3503904","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3503904","url":null,"abstract":"Accurate and fast per-flow size traffic measurement is fundamental to some network applications, especially in face of the processing and memory constraints of switches. Sketch, a compact data structure, can output high-fidelity approximate per-flow statistics. However, most existing sketches, such as Count-Min, are trapped in the dilemma between a large counting range and memory waste, due to the highly skewed characteristics of network traffic size distribution. In this paper, we propose an adaptive counter-splicing-based sketch for per-flow size measurement, called TailoredSketch. Specifically, we divide each counter of TailoredSketch into two parts, named basic and carry-in counters. When the basic counters overflow, the carry-in counters work, and meanwhile several carry-in counters in different positions can be spliced to expand the counting range. We also incorporate sampling into TailoredSketch, where we set different sampling probabilities at each layer to distinguish between elephant and mouse flows better. In order to further increase the memory utilization of TailoredSketch, we optimize it by removing the flag bits of each counter. Extensive experiments based on the real-world dataset CAIDA show that our sketch can achieve better overall performance compared to several existing algorithms.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"505-517"},"PeriodicalIF":6.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880338","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 : 2024-11-21DOI: 10.1109/TNSE.2024.3501378
Zhihui Wang;Jianrui Chen;Maoguo Gong;Fei Hao
With the increasing magnitude and complexity of data, the importance of higher-order networks is increasingly prominent. Dynamic hyperedge prediction reveals potential higher-order patterns with time evolution in networks, thus providing beneficial insights for decision making. Nevertheless, most existing neural network-based hyperedge prediction models are limited to static hypergraphs. Furthermore, previous efforts on hypergraph contrastive learning involve augmentation strategies, with insufficient consideration of the higher-order and lower-order views carried by the hypergraph itself. To address the above issues, we propose PCL-HP, a physics-guided hypergraph contrastive learning framework for dynamic hyperedge prediction. Specifically, we simply distinguish higher-order and lower-order views of the hypergraph to perform dynamic hypergraph contrastive learning and obtain abstract and concrete feature information, respectively. For lower-order views, we propose a physics-guided desynchronization mechanism to effectively guide the encoder to fuse the physical information during feature propagation, thus alleviating the problem of feature over-smoothing. Additionally, residual loss is introduced into the optimization process to incrementally quantify the loss at different stages to enhance the learning capability of the model. Extensive experiments on 10 dynamic higher-order datasets indicate that PCL-HP outperforms state-of-the-art baselines.
{"title":"Physics-Guided Hypergraph Contrastive Learning for Dynamic Hyperedge Prediction","authors":"Zhihui Wang;Jianrui Chen;Maoguo Gong;Fei Hao","doi":"10.1109/TNSE.2024.3501378","DOIUrl":"https://doi.org/10.1109/TNSE.2024.3501378","url":null,"abstract":"With the increasing magnitude and complexity of data, the importance of higher-order networks is increasingly prominent. Dynamic hyperedge prediction reveals potential higher-order patterns with time evolution in networks, thus providing beneficial insights for decision making. Nevertheless, most existing neural network-based hyperedge prediction models are limited to static hypergraphs. Furthermore, previous efforts on hypergraph contrastive learning involve augmentation strategies, with insufficient consideration of the higher-order and lower-order views carried by the hypergraph itself. To address the above issues, we propose PCL-HP, a physics-guided hypergraph contrastive learning framework for dynamic hyperedge prediction. Specifically, we simply distinguish higher-order and lower-order views of the hypergraph to perform dynamic hypergraph contrastive learning and obtain abstract and concrete feature information, respectively. For lower-order views, we propose a physics-guided desynchronization mechanism to effectively guide the encoder to fuse the physical information during feature propagation, thus alleviating the problem of feature over-smoothing. Additionally, residual loss is introduced into the optimization process to incrementally quantify the loss at different stages to enhance the learning capability of the model. Extensive experiments on 10 dynamic higher-order datasets indicate that PCL-HP outperforms state-of-the-art baselines.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 1","pages":"433-450"},"PeriodicalIF":6.7,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880409","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：