本文提出关系超图链接预测框架，使图神经网络适用于 k 元完全关系结构，并结合关系型 Weisfeiler-Leman 算法与逻辑表达性分析其能力，实验在归纳式和直推式任务上取得优异结果。
摘要：
在图机器学习中，基于知识图谱的链接预测已得到深入研究，形成了丰富的图神经网络架构体系，并取得了成功应用。然而，将这些架构的成功迁移到关系超图仍然具有挑战性：在关系超图中，链接预测任务针对的是 k 元关系，其难度显著高于基于知识图谱的链接预测。本文提出了一个用于关系超图链接预测的框架，使图神经网络能够应用于完全关系结构。在理论方面，我们通过相应的关系型 Weisfeiler-Leman 算法以及逻辑表达能力，对所得模型架构的表达能力进行了全面分析。在实验方面，我们在多个关系超图基准上验证了所提模型架构的能力。所得模型架构在归纳式链接预测上显著优于所有基线，并在直推式链接预测上取得了最先进结果。
英文摘要：
Link prediction with knowledge graphs has been thoroughly studied in graph machine learning, leading to a rich landscape of graph neural network architectures with successful applications. Nonetheless, it remains challenging to transfer the success of these architectures to relational hypergraphs, where the task of link prediction is over $k$-ary relations, which is substantially harder than link prediction with knowledge graphs. In this paper, we propose a framework for link prediction with relational hypergraphs, unlocking applications of graph neural networks to fully relational structures. Theoretically, we conduct a thorough analysis of the expressive power of the resulting model architectures via corresponding relational Weisfeiler-Leman algorithms and also via logical expressiveness. Empirically, we validate the power of the proposed model architectures on various relational hypergraph benchmarks. The resulting model architectures substantially outperform every baseline for inductive link prediction, and lead to state-of-the-art results for transductive link prediction.
Hyperbolic Hypergraph Neural Networks for Multi-Relational Knowledge Hypergraph Representation
National Engineering Research Center for Big Data Technology and System（国家大数据技术与系统工程研究中心）；School of Computer Science and Technology（计算机科学与技术学院）；Huazhong University of Science and Technology（华中科技大学）
Relational Learning in Pre-Trained Models: A Theory from Hypergraph Recovery Perspective
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；University of Illinois Chicago（芝加哥大学伊利诺伊分校）
Arizona State University（亚利桑那州立大学）；University of Illinois Chicago（伊利诺伊大学芝加哥分校）；Bytedance（字节跳动）；Illinois Institute of Technology（伊利诺伊理工学院）
Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to its elaborately fabricated contents, making it difficult to obtain large-scale annotations for fake news data. Due to such data scarcity issues, detecting fake news tends to fail and overfit in the supervised setting. Recently, graph neural networks (GNNs) have been adopted to leverage the richer relational information among both labeled and unlabeled instances. Despite their promising results, they are inherently f…
Uppsala University（乌普萨拉大学）；University of Regensburg（雷根斯堡大学）；Microsoft Research（微软研究院）
Learning program semantics from raw source code is challenging due to the complexity of real-world programming language syntax and due to the difficulty of reconstructing long-distance relational information implicitly represented in programs using identifiers. Addressing the first point, we consider Constrained Horn Clauses (CHCs) as a standard representation of program verification problems, providing a simple and programming language-independent syntax. For the second challenge, we explore graph representations of CHCs, and propose a new Relational Hypergraph Neural Network (R-HyGNN) archit…
We propose the Relational Tucker3 (RT) decomposition for multi-relational link prediction in knowledge graphs. We show that many existing knowledge graph embedding models are special cases of the RT decomposition with certain predefined sparsity patterns in its components. In contrast to these prior models, RT decouples the sizes of entity and relation embeddings, allows parameter sharing across relations, and does not make use of a predefined sparsity pattern. We use the RT decomposition as a tool to explore whether it is possible and beneficial to automatically learn sparsity patterns, and w…
University of Bonn（波恩大学）；Fraunhofer Institute for Intelligent Analysis and Information Systems (IAIS)（弗劳恩霍夫智能分析与信息系统研究所（IAIS））；Ludwig-Maximilians-Universität München（慕尼黑路德维希-马克西米利安大学（慕尼黑大学））；McGill University（麦吉尔大学）；Mila（米拉研究所）；IBM Research（IBM研究院）；Siemens AG（西门子股份公司）
For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based \glspl{kg}, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- a…
Institute of Informatics, UFRGS（UFRGS信息学院）；City, University of London（伦敦大学城市学院）
The recent developments and growing interest in neural-symbolic models has shown that hybrid approaches can offer richer models for Artificial Intelligence. The integration of effective relational learning and reasoning methods is one of the key challenges in this direction, as neural learning and symbolic reasoning offer complementary characteristics that can benefit the development of AI systems. Relational labelling or link prediction on knowledge graphs has become one of the main problems in deep learning-based natural language processing research. Moreover, other fields which make use of …
Knowledge graphs have emerged as an important model for studying complex multi-relational data. This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources. An effective and scalable approach to jointly learn over multiple graphs and eventually construct a unified graph is a crucial next step for the success of knowledge-based inference for many downstream applications. To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multipl…
FGeo-HyperGNet: Geometric Problem Solving Integrating FormalGeo Symbolic System and Hypergraph Neural Network
School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；School of Future Technology, Shanghai University（上海大学未来技术学院）；College of Sciences, Shanghai University（上海大学理学院）
University of British Columbia（不列颠哥伦比亚大学）；Element AI
Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation. Current methods do not capture the procedural rules underlying the relations in the graph. We propose a simple embedding-based model called ReAlE that performs link prediction in knowledge hypergraphs (generalized knowledge graphs) and can represent high-level abstractions in terms of relational algebra operations. We show theoretically that ReAlE is fully expressive and provide proofs and empirical evidence that it can represent a large subset of the primitive relational algebra…
School of Statistics and Data Science, Nankai University（南开大学统计与数据科学学院）；Department of Computer Science, University of California, Los Angeles（加利福尼亚大学洛杉矶分校计算机系）
Multi-Relational Knowledge Graph Enhanced Embedding for Trajectory-User Linking
the College of Information, Mechanical and Electrical Engineering, Shanghai Normal University（上海师范大学信息与机电工程学院）；Shanghai Urban-Rural Construction & Transportation Development Institute（上海城乡建设与交通发展研究院）；Zhongke Zidong Information Technology（中科紫东信息技术（北京）有限公司）
The University of Texas at Austin（得克萨斯大学奥斯汀分校）；The University of Tehran（德黑兰大学）；Stanford University（斯坦福大学）
Many problems such as node classification and link prediction in network data can be solved using graph embeddings. However, it is difficult to use graphs to capture non-binary relations such as communities of nodes. These kinds of complex relations are expressed more naturally as hypergraphs. While hypergraphs are a generalization of graphs, state-of-the-art graph embedding techniques are not adequate for solving prediction and classification tasks on large hypergraphs accurately in reasonable time. In this paper, we introduce HyperNetVec, a novel hierarchical framework for scalable unsupervi…
Hypergraph-based Motion Generation with Multi-modal Interaction Relational Reasoning
organization= Center for Geospatial Sciences, Applications；Department of Landscape of Architecture；Urban Planning, Texas A\&M University , addressline= 788 Ross St , city= College Station , postcode= 77840 , state= TX , country= United States；organization= Zachry Department of Civil；Environmental Engineering, Texas A\&M University , addressline= 201 Dwight Look Engineering Building , city= College Station , postcode= 77843 , state= TX , country= United States；organization= Department of Civil；Environmental Engineering, University of Wisconsin-Madison , addressline= 1415 Engineering Dr , city= Madison , postcode= 53706 , state= WI , country= United States
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Demystifying the interactions among multiple agents from their past trajectories is fundamental to precise and interpretable trajectory prediction. However, previous works only consider pair-wise interactions with limited relational reasoning. To promote more comprehensive interaction modeling for relational reasoning, we propose GroupNet, a multiscale hypergraph neural network, which is novel in terms of both interaction capturing and representation learning. From the aspect of interaction capturing, we propose a trainable multiscale hypergraph to capture both pair-wise and group-wise interac…
Predicting the future price trends of stocks is a challenging yet intriguing problem given its critical role to help investors make profitable decisions. In this paper, we present a collaborative temporal-relational modeling framework for end-to-end stock trend prediction. The temporal dynamics of stocks is firstly captured with an attention-based recurrent neural network. Then, different from existing studies relying on the pairwise correlations between stocks, we argue that stocks are naturally connected as a collective group, and introduce the hypergraph structures to jointly characterize t…
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
The Chinese University of Hong Kong.（香港中文大学）；Pengcheng Laboratory.（鹏城实验室）；WeChat AI, Tencent（微信AI，腾讯）；University of Chinese Academy of Sciences.（中国科学院大学）
HAHE: Hierarchical Attention for Hyper-Relational Knowledge Graphs in Global and Local Level
Beijing University of Posts and Telecommunications（北京邮电大学）；Beihang University（北京航空航天大学）；Beijing Institute of Computer Technology and Application（北京计算机技术及应用研究所）；Inspur Group Co., Ltd.（浪潮集团有限公司）
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）
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
With the overwhelming popularity of Knowledge Graphs (KGs), researchers have poured attention to link prediction to fill in missing facts for a long time. However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity). In practice, n-ary relational facts are also ubiquitous. When encountering such facts, existing studies usually decompose them into triples by introducing a multitude of auxiliary virtual entities and additional triples. These conversions result in the complexity of carry…
Stanford University（斯坦福大学）；Korea Advanced Institute of Science and Technology（韩国科学技术院）；University of California, Berkeley（加州大学伯克利分校）
While the modeling of pair-wise relations has been widely studied in multi-agent interacting systems, its ability to capture higher-level and larger-scale group-wise activities is limited. In this paper, we propose a group-aware relational reasoning approach (named EvolveHypergraph) with explicit inference of the underlying dynamically evolving relational structures, and we demonstrate its effectiveness for multi-agent trajectory prediction. In addition to the edges between a pair of nodes (i.e., agents), we propose to infer hyperedges that adaptively connect multiple nodes to enable group-awa…
The University of Tokyo（东京大学）；Imperial College London（帝国理工学院）；Osaka University（大阪大学）
The graph Laplacian plays key roles in information processing of relational data, and has analogies with the Laplacian in differential geometry. In this paper, we generalize the analogy between graph Laplacian and differential geometry to the hypergraph setting, and propose a novel hypergraph $p$-Laplacian. Unlike the existing two-node graph Laplacians, this generalization makes it possible to analyze hypergraphs, where the edges are allowed to connect any number of nodes. Moreover, we propose a semi-supervised learning method based on the proposed hypergraph $p$-Laplacian, and formalize them …
Multi-relational graph is a ubiquitous and important data structure, allowing flexible representation of multiple types of interactions and relations between entities. Similar to other graph-structured data, link prediction is one of the most important tasks on multi-relational graphs and is often used for knowledge completion. When related graphs coexist, it is of great benefit to build a larger graph via integrating the smaller ones. The integration requires predicting hidden relational connections between entities belonged to different graphs (inter-domain link prediction). However, this po…
School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Graph Attention Network (GAT) focuses on modelling simple undirected and single relational graph data only. This limits its ability to deal with more general and complex multi-relational graphs that contain entities with directed links of different labels (e.g., knowledge graphs). Therefore, directly applying GAT on multi-relational graphs leads to sub-optimal solutions. To tackle this issue, we propose r-GAT, a relational graph attention network to learn multi-channel entity representations. Specifically, each channel corresponds to a latent semantic aspect of an entity. This enables us to ag…
Reasoning about the relationships between entities from input facts (e.g., whether Ari is a grandparent of Charlie) generally requires explicit consideration of other entities that are not mentioned in the query (e.g., the parents of Charlie). In this paper, we present an approach for learning to solve problems of this kind in large, real-world domains, using sparse and local hypergraph neural networks (SpaLoc). SpaLoc is motivated by two observations from traditional logic-based reasoning: relational inferences usually apply locally (i.e., involve only a small number of individuals), and rela…
Biological and cellular systems are often modeled as graphs in which vertices represent objects of interest (genes, proteins, drugs) and edges represent relational ties among these objects (binds-to, interacts-with, regulates). This approach has been highly successful owing to the theory, methodology and software that support analysis and learning on graphs. Graphs, however, often suffer from information loss when modeling physical systems due to their inability to accurately represent multiobject relationships. Hypergraphs, a generalization of graphs, provide a framework to mitigate informati…
Purdue University（普渡大学）；Amazon Web Services（亚马逊云科技）
Graph representation learning has made major strides over the past decade. However, in many relational domains, the input data are not suited for simple graph representations as the relationships between entities go beyond pairwise interactions. In such cases, the relationships in the data are better represented as hyperedges (set of entities) of a non-uniform hypergraph. While there have been works on principled methods for learning representations of nodes of a hypergraph, these approaches are limited in their applicability to tasks on non-uniform hypergraphs (hyperedges with different cardi…
University of Amsterdam（阿姆斯特丹大学）；Indian Institute of Technology Dhanbad（印度理工学院丹巴德分校）；AIQ
Graphs are the most ubiquitous data structures for representing relational datasets and performing inferences in them. They model, however, only pairwise relations between nodes and are not designed for encoding the higher-order relations. This drawback is mitigated by hypergraphs, in which an edge can connect an arbitrary number of nodes. Most hypergraph learning approaches convert the hypergraph structure to that of a graph and then deploy existing geometric deep learning methods. This transformation leads to information loss, and sub-optimal exploitation of the hypergraph's expressive power…
University of Mannheim（曼海姆大学）；The University of Hong Kong（香港大学）
We study bilinear embedding models for the task of multi-relational link prediction and knowledge graph completion. Bilinear models belong to the most basic models for this task, they are comparably efficient to train and use, and they can provide good prediction performance. The main goal of this paper is to explore the expressiveness of and the connections between various bilinear models proposed in the literature. In particular, a substantial number of models can be represented as bilinear models with certain additional constraints enforced on the embeddings. We explore whether or not these…
University College London（伦敦大学学院）；Institute of Health Informatics（健康信息学研究所）
Learning knowledge representation is an increasingly important technology applicable in many domain-specific machine learning problems. We discuss the effectiveness of traditional Link Prediction or Knowledge Graph Completion evaluation protocol when embedding knowledge representation for categorised multi-relational data in the clinical domain. Link prediction uses to split the data into training and evaluation subsets, leading to loss of information along training and harming the knowledge representation model accuracy. We propose a Clustering Evaluation Protocol as a replacement alternative…
Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
POSTECH；Center for Geometry and Physics, Institute for Basic Science (IBS)（几何与物理中心，基础科学研究所）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction. This paper presents a Bayesian probabilistic approach that incorporates various kinds of node attributes encoded in binary form in relational models with Poisson likelihood. Our method works flexibly with both directed and undirected relational networks. The inference can be done by efficient Gibbs sampling which leverages sparsity of both networks and node attributes. Extensive experiments show that our models achieve …
LS2N, UMR CNRS 6004（LS2N，法国国家科学研究中心联合研究单位6004）；University of Nantes（南特大学）
Most of metric learning approaches are dedicated to be applied on data described by feature vectors, with some notable exceptions such as times series, trees or graphs. The objective of this paper is to propose a metric learning algorithm that specifically considers relational data. The proposed approach can take benefit from both the topological structure of the data and supervised labels. For selecting relative constraints representing the relational information, we introduce a link-strength function that measures the strength of relationship links between entities by the side-information of…
