Department of Computer Science and Technology, University of Cambridge（计算机科学与技术系，剑桥大学）；Department of Electrical and Computer Engineering, Northeastern University（电气与计算机工程系，东北大学）；Department of Computer, Control and Management Engineering, Sapienza University of Rome（计算机、控制与管理工程系，罗马萨皮恩扎大学）
Luke Braithwaite, Alessio Borgi, Gabriele Onorato, Kristjan Tarantelli, Francesco Restuccia, Fabrizio Silvestri, Pietro Liò
Heterogeneous graphs, whose nodes and edges can belong to different types and feature spaces, arise in many real-world domains, including biology, recommendation, social networks, and computer systems. Existing heterogeneous graph neural networks typically handle this heterogeneity at the architectural level through relation-specific modules, meta-path machinery or type-aware attention, which often leads to increasingly specialised parameter-heavy designs. In this work, we propose HetSheaf, a framework for learning heterogeneous graphs through cellular sheaves. Instead of encoding heterogeneity solely in the architecture, HetSheaf represents it directly in the underlying data structure by assigning type-aware local feature spaces and learning restriction maps conditioned on node features, node types, and edge types. To support graph-level prediction, we further introduce SheafPool, a universal stalk-space readout that aggregates node representations while being invariant to local changes of basis, thereby making graph classification with sheaf networks well-defined and achieving an F1 Score up to 42 percentage points higher than mean pooling. Across a diverse suite of benchmarks (node classification, link prediction and graph classification). HetSheaf consistently achieves up to 2 percentage points higher performance (up to 94.97% Macro F1 Score on node classification and up to 99.62% on link prediction) on the Heterogeneous Graph Benchmark (HGB) framework against homogeneous (GCN, GAT, GIN, GraphSAGE), heterogeneous (R-GCN, HAT, HGT) and type-agnostic sheaf baselines, while reducing the number of parameters by up to 10$\times$.
Dynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning
Peter L. Reichertz Institute for Medical Informatics（汉诺威医学院彼得·L·里赫茨医学信息学研究所）；Hannover Medical School（汉诺威医学院）；Lower Saxony Center for Artificial Intelligence and Causal Methods in Medicine (CAIMed)（下萨克森人工智能与医学因果方法中心（CAIMed））
The Ohio State University（俄亥俄州立大学）；University of Minnesota（明尼苏达大学）
We present a generalization of graph convolutional networks by generalizing the diffusion operation underlying this class of graph neural networks. These sheaf neural networks are based on the sheaf Laplacian, a generalization of the graph Laplacian that encodes additional relational structure parameterized by the underlying graph. The sheaf Laplacian and associated matrices provide an extended version of the diffusion operation in graph convolutional networks, providing a proper generalization for domains where relations between nodes are non-constant, asymmetric, and varying in dimension. We…
University of Cambridge（剑桥大学）；Twitter（推特）；University of Oxford（牛津大学）
Cellular sheaves equip graphs with a "geometrical" structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This choice is reflected in the structure of the graph Laplacian operator, the properties of the associated diffusion equation, and the characteristics of the convolutional models that discretise this equation. In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their ov…
University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Twitter（推特）；DeepMind（深度思维）
A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear maps between these spaces. SNNs have been shown to have useful theoretical properties that help tackle issues arising from heterophily and over-smoothing. One complication intrinsic to these models is finding a good sheaf for the task to be solved. Previous works proposed two diametrically opposed approaches: manually constructing the sheaf based on domain knowledge and learning the sheaf end-to-end using gradient-ba…
ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular Sheaves
Peter L. Reichertz Institute for Medical Informatics（彼得·L·赖歇茨医学信息学研究所）；Hannover Medical School（汉诺威医学院）；Lower Saxony Center for Artificial Intelligence and Causal Methods in Medicine (CAIMed)（下萨克森州人工智能与医学因果方法中心（CAIMed））
Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion
IUF – Leibniz Research Institute for Environmental Medicine（莱比锡环境医学研究所）；DNTOX GmbH（DNTOX公司）；Bioinformatics Group, Ruhr University Bochum（博德姆鲁尔大学生物信息学小组）；Swiss Centre for Applied Human Toxicology (SCAHT)（瑞士应用人类毒理学中心（SCAHT））
Graph convolutional networks are a popular class of deep neural network algorithms which have shown success in a number of relational learning tasks. Despite their success, graph convolutional networks exhibit a number of peculiar features, including a bias towards learning oversmoothed and homophilic functions, which are not easily diagnosed due to the complex nature of these algorithms. We propose to bridge this gap in understanding by studying the neural tangent kernel of sheaf convolutional networks--a topological generalization of graph convolutional networks. To this end, we derive a par…
We consider feature representation learning problem of molecular graphs. Graph Neural Networks have been widely used in feature representation learning of molecular graphs. However, most existing methods deal with molecular graphs individually while neglecting their connections, such as motif-level relationships. We propose a novel molecular graph representation learning method by constructing a heterogeneous motif graph to address this issue. In particular, we build a heterogeneous motif graph that contains motif nodes and molecular nodes. Each motif node corresponds to a motif extracted from…
Simple and Efficient Heterogeneous Graph Neural Network
Institute for Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Griffith University（格里菲斯大学）；University of Chinese Academy of Sciences（中国科学院大学）
University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；Beihang University（北京航空航天大学）；Lehigh University（理海大学）
Mining Electronic Health Records (EHRs) becomes a promising topic because of the rich information they contain. By learning from EHRs, machine learning models can be built to help human experts to make medical decisions and thus improve healthcare quality. Recently, many models based on sequential or graph models are proposed to achieve this goal. EHRs contain multiple entities and relations and can be viewed as a heterogeneous graph. However, previous studies ignore the heterogeneity in EHRs. On the other hand, current heterogeneous graph neural networks cannot be simply used on an EHR graph …
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Zhejiang University（浙江大学）
Researchers have recently proposed plenty of heterogeneous graph neural networks (HGNNs) due to the ubiquity of heterogeneous graphs in both academic and industrial areas. Instead of pursuing a more powerful HGNN model, in this paper, we are interested in devising a versatile plug-and-play module, which accounts for distilling relational knowledge from pre-trained HGNNs. To the best of our knowledge, we are the first to propose a HIgh-order RElational (HIRE) knowledge distillation framework on heterogeneous graphs, which can significantly boost the prediction performance regardless of model ar…
HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学现代软件技术国家重点实验室）；Research Center for Graph Computing, Zhejiang Lab（浙江实验室图计算研究中心）
Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
School of Statistics and Mathematics, Guangdong University of Finance & Economics（广东金融学院统计与数学学院）；School of Digital Economics, Guangdong University of Finance & Economics（广东金融学院数字经济学学院）
Many real-world data can be modeled as heterogeneous graphs that contain multiple types of nodes and edges. Meanwhile, due to excellent performance, heterogeneous graph neural networks (GNNs) have received more and more attention. However, the existing work mainly focuses on the design of novel GNN models, while ignoring another important issue that also has a large impact on the model performance, namely the missing attributes of some node types. The handcrafted attribute completion requires huge expert experience and domain knowledge. Also, considering the differences in semantic characteris…
New York University（纽约大学）；Facebook AI Research（Facebook人工智能研究院）
Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks by simply operating on graph-smoothed node features, rather than using end-to-end learned feature hierarchies that are challenging to scale to large graphs. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities. We propose Neighbor Averaging over Relation…
Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning
Tianjin University（天津大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；The Hong Kong Polytechnic University（香港理工大学）；University of Alberta（阿尔伯塔大学）
Heterogeneous graph neural networks (HGNNs) have been widely applied in heterogeneous information network tasks, while most HGNNs suffer from poor scalability or weak representation when they are applied to large-scale heterogeneous graphs. To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning. Unlike traditional heterogeneous graph neural networks, we adopt the contrastive learning mechanism to deal with the complex heterogeneity of large-scale heterogeneous g…
This work proposes a neural network architecture that learns policies for multiple agent classes in a heterogeneous multi-agent reinforcement setting. The proposed network uses directed labeled graph representations for states, encodes feature vectors of different sizes for different entity classes, uses relational graph convolution layers to model different communication channels between entity types and learns distinct policies for different agent classes, sharing parameters wherever possible. Results have shown that specializing the communication channels between entity classes is a promisi…
Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huazhong University of Science and Technology（华中科技大学）；Singapore Management University（新加坡管理大学）
Graph neural networks for heterogeneous graph embedding is to project nodes into a low-dimensional space by exploring the heterogeneity and semantics of the heterogeneous graph. However, on the one hand, most of existing heterogeneous graph embedding methods either insufficiently model the local structure under specific semantic, or neglect the heterogeneity when aggregating information from it. On the other hand, representations from multiple semantics are not comprehensively integrated to obtain versatile node embeddings. To address the problem, we propose a Heterogeneous Graph Neural Networ…
Sun Yat-sen University（中山大学）；Microsoft Research Asia（微软亚洲研究院）
Many real-world graphs (networks) are heterogeneous with different types of nodes and edges. Heterogeneous graph embedding, aiming at learning the low-dimensional node representations of a heterogeneous graph, is vital for various downstream applications. Many meta-path based embedding methods have been proposed to learn the semantic information of heterogeneous graphs in recent years. However, most of the existing techniques overlook the graph structure information when learning the heterogeneous graph embeddings. This paper proposes a novel Structure-Aware Heterogeneous Graph Neural Network …
Beijing University of Posts and Telecommunications（北京邮电大学）；Peng Cheng Laboratory（鹏城实验室）；AWS Shanghai AI Lab（亚马逊云科技上海人工智能实验室）；Paradigm Inc.（第四范式）
Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform …
Guangxi Normal University（广西师范大学）；Beihang University（北京航空航天大学）；Macquarie University（麦考瑞大学）
Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspects of information about individuals in the training stage. That means more information has been covered in the learning result, especially sensitive information. However, the privacy-preserving methods on homogeneous graphs only preserve the same type of node attributes or relationships, which cannot effectively work on heterogeneous graphs due to the complexity. To address this issue, we propose a novel heterogeneo…
A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations. Existing models usually define multiple metapaths in a heterogeneous graph to capture the composite relations and guide neighbor selection. However, these models either omit node content features, discard intermediate nodes along the metapath, or only consider one metapath. To address these three limitations, we p…
Seoul National University（首尔国立大学）；University of Michigan（密歇根大学）；Amazon Web Services（亚马逊云科技）
Heterogeneous graph neural networks (GNNs) achieve strong performance on node classification tasks in a semi-supervised learning setting. However, as in the simpler homogeneous GNN case, message-passing-based heterogeneous GNNs may struggle to balance between resisting the oversmoothing that may occur in deep models, and capturing long-range dependencies of graph structured data. Moreover, the complexity of this trade-off is compounded in the heterogeneous graph case due to the disparate heterophily relationships between nodes of different types. To address these issues, we propose a novel het…
Graph neural networks (GNN) extends deep learning to graph-structure dataset. Similar to Convolutional Neural Networks (CNN) using on image prediction, convolutional and pooling layers are the foundation to success for GNN on graph prediction tasks. In the initial PAN paper, it uses a path integral based graph neural networks for graph prediction. Specifically, it uses a convolution operation that involves every path linking the message sender and receiver with learnable weights depending on the path length, which corresponds to the maximal entropy random walk. It further generalizes such conv…
Ant Financial Services Group（蚂蚁金融服务集团）；Georgia Institute of Technology（佐治亚理工学院）
We present, GEM, the first heterogeneous graph neural network approach for detecting malicious accounts at Alipay, one of the world's leading mobile cashless payment platform. Our approach, inspired from a connected subgraph approach, adaptively learns discriminative embeddings from heterogeneous account-device graphs based on two fundamental weaknesses of attackers, i.e. device aggregation and activity aggregation. For the heterogeneous graph consists of various types of nodes, we propose an attention mechanism to learn the importance of different types of nodes, while using the sum operator …
Zhejiang University（浙江大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；JD.COM Silicon Valley Research Center（京东硅谷研发中心）；Squirrel AI Learning（松鼠AI智适应教育）
Crowdsourcing has attracted much attention for its convenience to collect labels from non-expert workers instead of experts. However, due to the high level of noise from the non-experts, an aggregation model that learns the true label by incorporating the source credibility is required. In this paper, we propose a novel framework based on graph neural networks for aggregating crowd labels. We construct a heterogeneous graph between workers and tasks and derive a new graph neural network to learn the representations of nodes and the true labels. Besides, we exploit the unknown latent interactio…
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspect extraction) and the sentiment polarities (sentiment detection) towards them. Both the previous pipeline and integrated methods fail to precisely model the innate connection between these two objectives. In this paper, we propose a novel dynamic heterogeneous graph to jointly model the two objectives in an explicit way. Both the ordinary words and sentiment labels are treated as nodes in the heterogeneous graph, so that the aspect words can interact with the sentiment information. The graph is initialized with multiple t…
Tsinghua University（清华大学）；Chinese Academy of Sciences（中国科学院）；Alibaba Group（阿里巴巴集团）；University of Pennsylvania（宾夕法尼亚大学）；Microsoft（微软）
Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs a…
Chemistry research has both high material and computational costs to conduct experiments. Institutions thus consider chemical data to be valuable and there have been few efforts to construct large public datasets for machine learning. Another challenge is that different intuitions are interested in different classes of molecules, creating heterogeneous data that cannot be easily joined by conventional distributed training. In this work, we introduce federated heterogeneous molecular learning to address these challenges. Federated learning allows end-users to build a global model collaborativel…
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology（大数据知识工程重点实验室（教育部））
