Heterogeneous graphs, comprising diverse node and edge types connected through varied relations, are ubiquitous in real-world applications. Message-passing heterogeneous graph neural networks (HGNNs) have emerged as a powerful model class for such data. However, existing HGNNs typically allocate a separate set of learnable weights for each relation type to model relational heterogeneity. Despite their promise, these models are effective primarily on simple heterogeneous graphs with only a few relation types. In this paper, we show that this standard design inherently leads to parameter explosion (the number of learnable parameters grows rapidly with the number of relation types) and relation collapse (the model loses the ability to distinguish among different relations). These issues make existing HGNNs inefficient or impractical for complex heterogeneous graphs with many relation types. To address these challenges, we propose Blend&Grind-HGNN (BG-HGNN), a unified feature-representation framework that integrates and distills relational heterogeneity into a shared low-dimensional feature space. This design eliminates the need for relation-specific parameter sets and enables efficient, expressive learning even as the number of relations grows. Empirically, BG-HGNN achieves substantial gains over state-of-the-art HGNNs, improving parameter efficiency by up to 28.96x and training throughput by up to 110.30x, while matching or surpassing their accuracy on complex heterogeneous graphs.
HIRE: Distilling High-order Relational Knowledge From Heterogeneous Graph Neural Networks
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)
Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph
Beihang University(北京航空航天大学);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所);BOSS Zhipin(BOSS直聘);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Predicting Drug-Drug Interactions Using Heterogeneous Graph Neural Networks: HGNN-DDI
College of Information Science and Engineering, Northeastern University(东北大学信息科学与工程学院);Lochlann Quinn School of Business, University College Dublin(都柏林大学学院洛克兰·奎因商学院);Faculty of Science, McGill University(麦吉尔大学理学院)
MG-HGNN: A Heterogeneous GNN Framework for Indoor Wi-Fi Fingerprint-Based Localization
School of Computer Science and Technology, Harbin Institute of Technology(计算机科学与技术学院,哈尔滨工业大学);China Mineral Resources Group Big Data Co., Ltd(中国矿产资源集团大数据有限公司);Tianhe Cyberspace Security Technology Research Institute Co.(天和网络空间安全技术研究所)
HeTa: Relation-wise Heterogeneous Graph Foundation Attack Model
School of Cyberspace, Hangzhou Dianzi University(电子科技大学信息学院);Data Security Governance Zhejiang Engineering Research Center, Hangzhou Dianzi University(浙江省数据安全治理工程研究中心);Beihang University(北航)
针对异质图神经网络攻击难以跨模型与跨图泛化的问题,提出 HeTa 基础攻击模型,利用共享关系感知攻击单元和逐关系序列化攻击实现可迁移、易适配的强攻击。
THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
Data Science Degree Program National Taiwan University;Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan;University of Illinois Urbana-Champaign Electrical \& Computer Engineering Illinois United States;Research Center for Information Technology Innovation Academia Sinica Taipei Taiwan;Department of Electrical Engineering National Taiwan University Taipei Taiwan;National Taiwan University;University of Illinois Urbana-Champaign
Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspective
College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学);Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY), Nanyang Technological University(老年人积极生活卓越研究中心(LILY),南洋理工大学);Alibaba-NTU Singapore Joint Research Institute (ANGEL), Nanyang Technological University(阿里巴巴-南洋理工大学新加坡联合研究机构(ANGEL),南洋理工大学)
Physics-Guided Dual-Stream Heterogeneous Graph Neural Network for Predicting Full-Field Structural Response of Stiffened Panels
Department of Mechanical Engineering, The University of British Columbia(不列颠哥伦比亚大学机械工程系);Department of Civil Engineering, The University of British Columbia(不列颠哥伦比亚大学土木工程系)
SiHGNN: Leveraging Properties of Semantic Graphs for Efficient HGNN Acceleration
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所 国家处理器重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Faculty of Computility Microelectronics, Shenzhen University of Advanced Technology(深圳先进技术学院 计算微电子学院)
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)
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)
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)
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))
Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks
Laboratory for Nuclear Science. Massachusetts Institute of Technology (MIT)(麻省理工学院核科学实验室);Experimental Physics Department, European Organization for Nuclear Research (CERN)(欧洲核子研究中心(CERN)实验物理部门)
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
University of Rome Tor Vergata(罗马大学Tor Vergata);University of Basel(巴塞尔大学);University of Rome Tor Vergata Harvard Medical School(罗马大学Tor Vergata哈佛医学院);Bocconi University Bocconi Institute for Data Science and Analytics(博科尼大学博科尼数据科学与分析研究所);UiT The Arctic University of Norway(UiT北极大学)
Teaching MLPs to Master Heterogeneous Graph-Structured Knowledge for Efficient and Accurate Inference
State Key Laboratory for Novel Software Technology, Nanjing University(新型软件技术国家重点实验室,南京大学);School of Information Technology and Electrical Engineering, The University of Queensland(信息科技与电气工程学院,昆士兰大学)