Papers with Code · CC BY-SA 4.0

Node Classification on Non-Homophilic (Heterophilic) Graphs

Node Classification › Node Classification on Non-Homophilic (Heterophilic) Graphs 401 평가 기록 15 datasets

There exists a non-trivial set of graphs where graph-aware models underperform their corresponding graph-agnostic models, e.g. SGC and GCN underperform MLP with 1 layer and 2 layers. Although still controversial, people believe the performance degradation results from heterophily, i.e. there exist much more inter-class edges than inner-class edges. This task aims to evaluate models designed for non-homophilic (heterophilic) datasets.

Node Classification on Non-Homophilic (Heterophilic) Graphs

논문

Revisiting Heterophily For Graph Neural Networks

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

Non-Local Graph Neural Networks

Finding Global Homophily in Graph Neural Networks When Meeting Heterophily

Adaptive Universal Generalized PageRank Graph Neural Network

Addressing Heterophily in Node Classification with Graph Echo State Networks

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

Beyond Low-frequency Information in Graph Convolutional Networks

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Deformable Graph Convolutional Networks

Edge Directionality Improves Learning on Heterophilic Graphs

Geom-GCN: Geometric Graph Convolutional Networks

Graph Attention Networks

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing

Scale Invariance of Graph Neural Networks

Simple and Deep Graph Convolutional Networks

Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks