Graph Heterophily

Follow this topic Ask about this topic

In heterophilic graphs, neighboring nodes may belong to different classes, so standard graph neural networks can blur useful distinctions by averaging their information. Methods address this with adaptive low- and high-pass filters, edge-aware or higher-order aggregation, graph rewiring, and separate treatment of node features and structure. Evaluation spans node classification, clustering, and text-attributed or heterogeneous graphs, but comparisons depend on dataset difficulty, feature quality, and careful tuning. A central open tension is that heterophily can be informative or misleading, so models must identify which connections carry useful signals rather than assume one strategy works across graphs.

Latest papers

25 papers0 papers in the last four weeks, down 100% on the four weeks before. 0.0% of all new papers.

HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs
Oct 27, 2026Xuanzhi Xi, Tongze Zhang, Zhili Qin +5Generalized Category Discovery Graph Neural Networks
University of Electronic Science and Technology of China, China
Beyond Fixed Features: Architecture-Dependent Sensitivity to Node Representations under Heterophily
Sep 27, 2026Priyanath Maji, Sidharth Gaur, Rajavinoth Paul DuraiGraph Neural Networks Graph Heterophily
Georgia Institute of Technology
Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification
Sep 26, 2026Harshit Kumar, Sujan Chakraborty, Priyanka Saha +2Graph Rewiring Graph Structure Learning
School of Data Science, Indian Institute of Science Education and Research Thiruvananthapuram, Thiruvananthapuram 695551, India
When Connected Does Not Mean Similar: Charting the Homophily Boundary of SNAP-KG for Streaming Entity Integration
Sep 11, 2026Jui-Chien Lin, Oshani SeneviratneMulti-View Clustering Graph Clustering
Rensselaer Polytechnic Institute, Troy, NY 12180, USA
HERALD: High-Fidelity Exemplar Retrieval with Adaptive Landmark Distillation for Heterophily-Aware Graph Condensation
Sep 10, 2026Sujan Chakraborty, Priyanka Saha, Saptarshi BejDataset Condensation Graph Heterophily
School of Data Science, Indian Institute of Science Education and Research Thiruvananthapuram, Thiruvananthapuram, 695551, Kerala, India
HOPE: Heterophily-Aware Open-Set Node Classification with Pseudo-Extrapolation
Sep 8, 2026Yumeng Dai, Yue Tan, Yixin Liu +3Graph Neural Networks Node Classification
Xi’an Jiaotong University, Xi’an, China · Griffith University, Brisbane, Australia
Disentangling Homophily and Rarity: Explaining Failure in Graph Neural Networks
Aug 14, 2026Preben M. Ness, Fariz Ikhwantri, Dusica MarijanGraph Neural Networks Node Classification
Simula Research Laboratory
HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks
Jul 28, 2026Phan Binh Nguyen Lam, Nguyen Thai AnhGraph Neural Networks Conformal Prediction
Faculty of Information Technology, University of Science, Vietnam National University, Ho Chi Minh City, Vietnam · Faculty of Information Technology, Van Lang School of Technology, Van Lang University, Ho Chi Minh City, Vietnam
Remedying Coarsening-Based GNN Training under Heterophily via Adaptive Complementary Enhancement
Jul 24, 2026Guoming Li, Jian Yang, Xukun Wang +3Graph Neural Networks Graph Coarsening
Department of Computer Science, Hong Kong Baptist University, Hong Kong SAR, China · School of Information, Renmin University of China, Beijing, China · Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China +2
Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs
Jun 29, 2026Feifan WangGraph Representation Learning Graph Clustering
School of Artificial Intelligence Xiamen Institute of Technology No. 1251, Sunban South Road, Jimei District Xiamen, Fujian 361021, China
Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs
Jun 5, 2026Takuto Takahashi, Itsuki Nakayama, Takahiro Mitani +3Graph Neural Networks Node Classification
The University of Osaka, 1-5 Yamadaoka, Suita, Osaka, Japan
Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification
May 12, 2026Kamel Abdous, Nairouz Mrabah, Mohamed BouguessaGraph Representation Learning Spectral Methods
Department of Computer Science, University of Quebec at Montreal, Montreal, QC, Canada
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
May 8, 2026Md Sazzad Hossen, Avimanyu SahooGraph Heterophily Over-Squashing
University of Alabama in Huntsville, Huntsville, AL, USA.
HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
May 6, 2026Xinyi Li, Ming Li, Lu Bai +5Heterogeneous GNNs Node Classification
Zhejiang Normal University · Beijing Normal University · Central University of Finance and Economics +2
Robust Learning on Heterogeneous Graphs with Heterophily: A Graph Structure Learning Approach
Apr 30, 2026Yihan Zhang, Ercan E. KuruogluGraph Structure Learning Graph Representation Learning
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
Layer Embedding Deep Fusion Graph Neural Network
Apr 25, 2026Taihua Xu, Genhao Tian, Jicong Fan +3Graph Structure Learning Graph Neural Networks
Jiangsu University of Science and Technology · The Chinese University of Hong Kong, Shenzhen · Chongqing University of Post and Telecommunications
F\textsuperscript{2}LP-AP: Fast & Flexible Label Propagation with Adaptive Propagation Kernel
Apr 22, 2026Yutong Shen, Ruizhe Xia, Jingyi Liu +1Graph-Based Semi-Supervised Learning Semi-Supervised Learning
Beijing University of Technology
Inductive Subgraphs as Shortcuts: Causal Disentanglement for Heterophilic Graph Learning
Apr 21, 2026Xiangmeng Wang, Qian Li, Haiyang Xia +3Disentangled Representation Learning Graph Neural Networks
Curtin University Perth, Australia · The Education University of Hong Kong New Territories, Hong Kong
NK-GAD: Neighbor Knowledge-Enhanced Unsupervised Graph Anomaly Detection
Apr 17, 2026Zehao Wang, Lanjun WangGraph Neural Networks Reconstruction-Based Anomaly Detection
College of Intelligence and Computing, Tianjin University, Tianjin, China · School of New Media and Communication, Tianjin University, Tianjin, China
Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning
Apr 10, 2026Yi Luo, Xu Sun, Guangchun Luo +1Graph Transformer Graph Heterophily
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China · School of Computer Science and Engineering, University of Electronic Science and Technology of China · Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province, China
Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?
Mar 25, 2026Eyal WeissGraph Neural Networks Graph Heterophily
Computer Science Faculty, Technion — Israel Institute of Technology
Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling
Mar 4, 2026Jiaqi Lv, Qingfeng Du, Yu Zhang +2Graph Neural Networks Graph Heterophily
School of Computer Science and Technology, Tongji University, Shanghai, China
HeTGB: A Comprehensive Benchmark for Heterophilic Text-Attributed Graphs
Mar 5, 2025Shujie Li, Yuxia Wu, Yuan Fang +1Text-Attributed Graph Learning Node Classification
Beijing University of Post and Telecommunication · Beijing, China · Singapore Management University +1
Revealing the Pitfalls and Re-Evaluating the Advancement of Heterophilic Graph Learning
Sep 9, 2024Sitao Luan, Qincheng Lu, Chenqing Hua +3Graph Neural Networks Node Classification
Mila - Quebec Artiﬁcial Intelligence Institute · 1McGill University
Provable Filter for Real-world Graph Clustering
Mar 6, 2024Xuanting Xie, Erlin Pan, Zhao Kang +2Graph Clustering Graph Heterophily
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · Alibaba Group · Michigan State University

Oct 27, 2026J/K move · Enter open · S save

HeteGCD: Statistics-Aware Dual-Prototype Learning for Generalized Category Discovery on Heterophilous Graphs

Xuanzhi Xi, Tongze Zhang, Zhili Qin, Yulin Tao+4

University of Electronic Science and Technology of China, China

Generalized Category Discovery Graph Neural Networks Prototype Learning Graph Heterophily

Open paper AskPDF arXiv

Heterophilous graphs are prevalent in real-world applications, where connected nodes often exhibit dissimilar attributes or belong to different classes, posing significant challenges to conventional graph learning methods based on homophily. This limitation becomes particularly pronounced in generalized category discovery (GCD), which requires models to recognize known classes and discover novel ones using labels from known classes only. However, existing graph GCD methods typically rely on aforementioned homophily-based inductive biases, which are ill-suited to heterophilous graphs. Meanwhile, although current heterophilous graph learning methods exploit diverse neighborhood signals, their selection and fusion are often guided by supervision across all classes, including novel classes whose labels are unavailable in GCD. These limitations raise a key question: how can heterogeneous neighborhood information be effectively leveraged for category discovery without any novel-class supervision? To answer this question, in this study we propose HeteGCD, a new statistics-aware dual-prototype learning perspective for generalized category discovery on heterophilous graphs. The key idea is to examine both statistics of local attribute differences and neighborhood class distribution to extract discriminative information in feature and probability spaces simultaneously. Specifically, a gated dual-stream encoder integrates both node attributes and local attribute-difference statistics to learn informative node representations. Afterwards, a dual-prototype classifier combines feature-based similarity with distribution-based consistency to support category discovery. Experiments on five heterophilous graphs show that HeteGCD achieves competitive performance against 24 baseline combinations.