A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions

Abstract

Graphs are structured data that models complex relations between real-world entities. Heterophilic graphs, where linked nodes are prone to be with different labels or dissimilar features, have recently attracted significant attention and found many real-world applications. Meanwhile, increasing efforts have been made to advance learning from graphs with heterophily. Various graph heterophily measures, benchmark datasets, and learning paradigms are emerging rapidly. In this survey, we comprehensively review existing works on learning from graphs with heterophily. First, we overview over 500 publications, of which more than 340 are directly related to heterophilic graphs. After that, we survey existing metrics of graph heterophily and list recent benchmark datasets. Further, we systematically categorize existing methods based on a hierarchical taxonomy including GNN models, learning paradigms and practical applications. In addition, broader topics related to graph heterophily are also included. Finally, we discuss the primary challenges of existing studies and highlight promising avenues for future research.

64 pages

References in corpus (43)

• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Neural Graph Collaborative Filtering
• Mixing patterns in networks
• Link Prediction in Complex Networks: A Survey
• Self-supervised Graph Learning for Recommendation
• Deep Learning in Spiking Neural Networks
• The spread of low-credibility content by social bots
• struc2vec: Learning Node Representations from Structural Identity
• Adversarial Attacks on Neural Networks for Graph Data
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Social Structure of Facebook Networks
• ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
• Towards Deeper Graph Neural Networks
• Disinformation and Social Bot Operations in the Run Up to the 2017 French Presidential Election
• The physics of brain network structure, function, and control
• GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks
• A Comprehensive Survey of Scene Graphs: Generation and Application
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• Conditional molecular design with deep generative models
• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
• Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket
• Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns
• A Survey of Large Language Models for Graphs
• Toward a Spectral Theory of Cellular Sheaves
• Label Information Enhanced Fraud Detection against Low Homophily in Graphs
• Learning Strong Graph Neural Networks with Weak Information
• LTE4G: Long-Tail Experts for Graph Neural Networks
• Robust Mid-Pass Filtering Graph Convolutional Networks
• UniG-Encoder: A Universal Feature Encoder for Graph and Hypergraph Node Classification
• Homophily-oriented Heterogeneous Graph Rewiring
• HetGPT: Harnessing the Power of Prompt Tuning in Pre-Trained Heterogeneous Graph Neural Networks
• SIGformer: Sign-aware Graph Transformer for Recommendation
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• How does Heterophily Impact the Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications
• Spatial Heterophily Aware Graph Neural Networks
• Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective
• GPT4Rec: Graph Prompt Tuning for Streaming Recommendation
• Disambiguated Node Classification with Graph Neural Networks
• Neighborhood Homophily-based Graph Convolutional Network
• PolyFormer: Scalable Node-wise Filters via Polynomial Graph Transformer
• Resurrecting Label Propagation for Graphs with Heterophily and Label Noise
• Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
• HC-GST: Heterophily-aware Distribution Consistency based Graph Self-training

Cited by in corpus (1)

• Introduction to Graph Neural Networks for Machine Learning Engineers