通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2506.17312cs.SIcs.AIcs.LG
异构时序超图神经网络
Heterogeneous Temporal Hypergraph Neural Network
School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学信息学院）；Data Security Governance Zhejiang Engineering Research Center（浙江数据安全治理工程研究中心）；College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；College of Intelligence and Computing, Tianjin University（天津大学智能与计算学院）
Huan Liu, Pengfei Jiao, Mengzhou Gao, Chaochao Chen, Di Jin
Graph representation learning (GRL) has emerged as an effective technique for modeling graph-structured data. When modeling heterogeneity and dynamics in real-world complex networks, GRL methods designed for complex heterogeneous temporal graphs (HTGs) have been proposed and have achieved successful applications in various fields. However, most existing GRL methods mainly focus on preserving the low-order topology information while ignoring higher-order group interaction relationships, which are more consistent with real-world networks. In addition, most existing hypergraph methods can only model static homogeneous graphs, limiting their ability to model high-order interactions in HTGs. Therefore, to simultaneously enable the GRL model to capture high-order interaction relationships in HTGs, we first propose a formal definition of heterogeneous temporal hypergraphs and $P$-uniform heterogeneous hyperedge construction algorithm that does not rely on additional information. Then, a novel Heterogeneous Temporal HyperGraph Neural network (HTHGN), is proposed to fully capture higher-order interactions in HTGs. HTHGN contains a hierarchical attention mechanism module that simultaneously performs temporal message-passing between heterogeneous nodes and hyperedges to capture rich semantics in a wider receptive field brought by hyperedges. Furthermore, HTHGN performs contrastive learning by maximizing the consistency between low-order correlated heterogeneous node pairs on HTG to avoid the low-order structural ambiguity issue. Detailed experimental results on three real-world HTG datasets verify the effectiveness of the proposed HTHGN for modeling high-order interactions in HTGs and demonstrate significant performance improvements.
Multi-Granular Attention based Heterogeneous Hypergraph Neural Network
School of Computer Science, Hubei University（湖北大学计算机学院）；Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University)（湖北大学大数据智能分析与应用重点实验室）；Discipline of Business Analytics, The University of Sydney（悉尼大学商业分析学科）；Key Laboratory of Intelligent Sensing System and Security (Hubei University), Ministry of Education（智能感知系统与安全重点实验室（湖北大学），教育部）
Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification
School of Computer Science and Technology, East China Normal University（计算机科学与技术学院，东华大学）；NPPA Key Laboratory of Publishing Integration Development, ECNUP（出版集成发展关键实验室，ECNUP）
DualHNIE: Dual-Channel Hypergraph Learning for Node Importance Estimation in Heterogeneous Knowledge Graphs
Jiangsu Key Laboratory of Networked Collective Intelligence, School of Mathematics, Southeast University（江苏网络集体智能重点实验室，数学学院，东南大学）；Jiangsu Key Laboratory of Networked Collective Intelligence, School of Cyber Science and Engineering, Southeast University（江苏网络集体智能重点实验室，网络科学与工程学院，东南大学）；State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, University of Chinese Academy of Sciences（数学科学国家重点实验室，数学与系统科学研究院，中国科学院大学）
South China University of Technology（华南理工大学）；Simon Fraser University（西蒙弗雷泽大学）；Musketeers Foundation Institute of Data Science（火枪手基金会数据科学研究院）；University of Hong Kong（香港大学）
Crime has become a major concern in many cities, which calls for the rising demand for timely predicting citywide crime occurrence. Accurate crime prediction results are vital for the beforehand decision-making of government to alleviate the increasing concern about the public safety. While many efforts have been devoted to proposing various spatial-temporal forecasting techniques to explore dependence across locations and time periods, most of them follow a supervised learning manner, which limits their spatial-temporal representation ability on sparse crime data. Inspired by the recent succe…
$\text{H}^2\text{TNE}$: Temporal Heterogeneous Information Network Embedding in Hyperbolic Spaces
College of Computer Science, Nankai University（南开大学计算机学院）；College of Cyber Science, Nankai University（南开大学网络空间安全学院）；TJ Key Laboratory of NDST, Nankai University（南开大学天津市NDST重点实验室）
Southern University of Science and Technology（南方科技大学）；Sun Yat-sen University（中山大学）
Tensor decomposition is an effective tool for learning multi-way structures and heterogeneous features from high-dimensional data, such as the multi-view images and multichannel electroencephalography (EEG) signals, are often represented by tensors. However, most of tensor decomposition methods are the linear feature extraction techniques, which are unable to reveal the nonlinear structure within high-dimensional data. To address such problem, a lot of algorithms have been proposed for simultaneously performs linear and non-linear feature extraction. A representative algorithm is the Graph Reg…
HGAurban: Heterogeneous Graph Autoencoding for Urban Spatial-Temporal Learning
The University of Hong Kong（香港大学）；The University of Queensland（昆士兰大学）；University of California, Los Angles（加州大学洛杉矶分校）；National University of Singapore（新加坡国立大学）
University of Hong Kong（香港大学）；National University of Singapore（新加坡国立大学）；Ocean University of China（中国海洋大学）；Wuhan University（武汉大学）
Learning dynamic user preference has become an increasingly important component for many online platforms (e.g., video-sharing sites, e-commerce systems) to make sequential recommendations. Previous works have made many efforts to model item-item transitions over user interaction sequences, based on various architectures, e.g., recurrent neural networks and self-attention mechanism. Recently emerged graph neural networks also serve as useful backbone models to capture item dependencies in sequential recommendation scenarios. Despite their effectiveness, existing methods have far focused on ite…
Heterogeneous Hypergraph Embedding for Recommendation Systems
Griffith University（格里菲斯大学）；Hanoi University of Science and Technology（河内科技大学）；Ecole Polytechnique Federale de Lausanne（洛桑联邦理工学院）；The University of Queensland（昆士兰大学）
Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergr…
Group interactions arise in our daily lives (email communications, on-demand ride sharing, comment interactions on online communities, to name a few), and they together form hypergraphs that evolve over time. Given such temporal hypergraphs, how can we describe their underlying design principles? If their sizes and time spans are considerably different, how can we compare their structural and temporal characteristics? In this work, we define 96 temporal hypergraph motifs (TH-motifs), and propose the relative occurrences of their instances as an answer to the above questions. TH-motifs categori…
Interactions involving multiple objects simultaneously are ubiquitous across many domains. The systems these interactions inhabit can be modelled using hypergraphs, a generalization of traditional graphs in which each edge can connect any number of nodes. Analyzing the global and static properties of these hypergraphs has led to a plethora of novel findings regarding how these modelled systems are structured. However, less is known about the localized structure of these systems and how they evolve over time. In this paper, we propose the study of hypergraph ego-networks, a structure that can b…
Dynamic systems that consist of a set of interacting elements can be abstracted as temporal networks. Recently, higher-order patterns that involve multiple interacting nodes have been found crucial to indicate domain-specific laws of different temporal networks. This posts us the challenge of designing more sophisticated hypergraph models for these higher-order patterns and the associated new learning algorithms. Here, we propose the first model, named HIT, for full-spectrum higher-order pattern prediction in temporal hypergraphs. Particularly, we focus on predicting three types of common but …
Many real-world complex systems are characterized by interactions in groups that change in time. Current temporal network approaches, however, are unable to describe group dynamics, as they are based on pairwise interactions only. Here, we use time-varying hypergraphs to describe such systems, and we introduce a framework based on higher-order correlations to characterize their temporal organization. We analyze various social systems, finding that groups of different sizes have typical patterns of long-range temporal correlations. Moreover, our method reveals the presence of non-trivial tempor…
We investigate consensus dynamics on temporal hypergraphs that encode network systems with time-dependent, multi-way interactions. We compare this dynamics with that on appropriate projections of this higher-order network representation that flatten the temporal, the multi-way component, or both. For linear average consensus dynamics, we find that the convergence of a randomly switching time-varying system with multi-way interactions is slower than the convergence of the corresponding system with pairwise interactions, which in turn exhibits a slower convergence rate than a consensus dynamics …
Northeastern University（东北大学）；Microsoft Research Asia（微软亚洲研究院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
With the development of temporal networks such as E-commerce networks and social networks, the issue of temporal link prediction has attracted increasing attention in recent years. The Temporal Link Prediction task of WSDM Cup 2022 expects a single model that can work well on two kinds of temporal graphs simultaneously, which have quite different characteristics and data properties, to predict whether a link of a given type will occur between two given nodes within a given time span. Our team, named as nothing here, regards this task as a link prediction task in heterogeneous temporal networks…
SourceDetMamba: A Graph-aware State Space Model for Source Detection in Sequential Hypergraphs
School of Artificial Intelligence, Optics and Electronics, Northwestern Polytechnical University（人工智能、光学与电子学院，西北工业大学）；School of Computer Science, Northwestern Polytechnical University（计算机科学学院，西北工业大学）；School of Cybersecurity, Northwestern Polytechnical University（网络安全学院，西北工业大学）；Cyberspace Institute of Advanced Technology, Guangzhou University（高级技术网络空间研究院，广州大学）
School of Airspace Science and Engineering, Shandong University（航空航天科学与工程学院，山东大学）；School of Mathematics and Statistics, Shandong University（数学与统计学院，山东大学）
The Australian National University（澳大利亚国立大学）；Alibaba Group（阿里巴巴集团）；National University of Singapore（新加坡国立大学）
A bipartite network is a graph structure where nodes are from two distinct domains and only inter-domain interactions exist as edges. A large number of network embedding methods exist to learn vectorial node representations from general graphs with both homogeneous and heterogeneous node and edge types, including some that can specifically model the distinct properties of bipartite networks. However, these methods are inadequate to model multiplex bipartite networks (e.g., in e-commerce), that have multiple types of interactions (e.g., click, inquiry, and buy) and node attributes. Most real-wo…
Many real systems are strongly characterized by collective cooperative phenomena whose existence and properties still need a satisfactory explanation. Coherently with their collective nature, they call for new and more accurate descriptions going beyond pairwise models, such as graphs, in which all the interactions are considered as involving only two individuals at a time. Hypergraphs respond to this need, providing a mathematical representation of a system allowing from pairs to larger groups. In this work, through the use of different hypergraphs, we study how group interactions influence t…
Case Western Reserve University（凯斯西储大学）；University of Notre Dame（圣母大学）；Brandeis University（布兰迪斯大学）；Emory University（埃默里大学）
Graph neural networks (GNNs) have been broadly studied on dynamic graphs for their representation learning, majority of which focus on graphs with homogeneous structures in the spatial domain. However, many real-world graphs - i.e., heterogeneous temporal graphs (HTGs) - evolve dynamically in the context of heterogeneous graph structures. The dynamics associated with heterogeneity have posed new challenges for HTG representation learning. To solve this problem, in this paper, we propose heterogeneous temporal graph neural network (HTGNN) to integrate both spatial and temporal dependencies whil…
Social networks are now ubiquitous and most of them contain interactions involving multiple actors (groups) like author collaborations, teams or emails in an organizations, etc. Hypergraphs are natural structures to effectively capture multi-actor interactions which conventional dyadic graphs fail to capture. In this work the problem of predicting collaborations is addressed while modeling the collaboration network as a hypergraph network. The problem of predicting future multi-actor collaboration is mapped to hyperedge prediction problem. Given that the higher order edge prediction is an inhe…
The Australian National University（澳大利亚国立大学）；Alibaba Group（阿里巴巴集团）
Network embedding aims to learn low-dimensional representations of nodes while capturing structure information of networks. It has achieved great success on many tasks of network analysis such as link prediction and node classification. Most of existing network embedding algorithms focus on how to learn static homogeneous networks effectively. However, networks in the real world are more complex, e.g., networks may consist of several types of nodes and edges (called heterogeneous information) and may vary over time in terms of dynamic nodes and edges (called evolutionary patterns). Limited wor…
Hypergraphs are a natural modeling paradigm for a wide range of complex relational systems. A standard analysis task is to identify clusters of closely related or densely interconnected nodes. Many graph algorithms for this task are based on variants of the stochastic blockmodel, a random graph with flexible cluster structure. However, there are few models and algorithms for hypergraph clustering. Here, we propose a Poisson degree-corrected hypergraph stochastic blockmodel (DCHSBM), a generative model of clustered hypergraphs with heterogeneous node degrees and edge sizes. Approximate maximum-…
Harbin Institute of Technology（哈尔滨工业大学）；Jilin University（吉林大学）；Peng Cheng Laboratory（鹏城实验室）；Nanyang Technological University（南洋理工大学）
Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data contains various features, node and edge types which dynamically vary over time, and this invalidates most existing community detection approaches. To cope with these issues, this paper proposes the heterogeneous-temporal graph convolutional networks (HTGCN) to detect communities from hetergeneous and temporal graphs. Particularly, we first design a heterogeneous GCN component to acquire feature repres…
Empirical temporal networks display strong heterogeneities in their dynamics, which profoundly affect processes taking place on these networks, such as rumor and epidemic spreading. Despite the recent wealth of data on temporal networks, little work has been devoted to the understanding of how such heterogeneities can emerge from microscopic mechanisms at the level of nodes and links. Here we show that long-term memory effects are present in the creation and disappearance of links in empirical networks. We thus consider a simple generative modeling framework for temporal networks able to incor…
Higher-order rich clubs and configuration models on general directed hypergraphs
Nottingham Trent University（诺丁汉特伦特大学）；Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克科学计量学研究所）；Institute of Clinical and Preventive Medicine, University of Latvia（拉脱维亚大学临床与预防医学研究所）；Graz University of Technology（格拉茨工业大学）；Computer and Information Sciences, University of Strathclyde（思克莱德大学计算机与信息科学学院）；Max Planck Institute of Molecular Cell Biology and Genetics (MPI-CBG)（马克斯·普朗克分子细胞生物学与遗传学研究所）；Center for Systems Biology Dresden (CSBD)（德累斯顿系统生物学中心）
