SOTAVerified

Node Classification on Non-Homophilic (Heterophilic) Graphs

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 29 papers

TitleStatusHype
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural NetworksCode1
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein ApproximationCode1
Beyond Low-frequency Information in Graph Convolutional NetworksCode1
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing PatternsCode1
Non-Local Graph Neural NetworksCode1
Revisiting Heterophily For Graph Neural NetworksCode1
Semi-Supervised Classification with Graph Convolutional NetworksCode1
Simple and Deep Graph Convolutional NetworksCode1
Simplifying Graph Convolutional NetworksCode1
Clenshaw Graph Neural NetworksCode1
Combining Label Propagation and Simple Models Out-performs Graph Neural NetworksCode1
Deformable Graph Convolutional NetworksCode1
Edge Directionality Improves Learning on Heterophilic GraphsCode1
Finding Global Homophily in Graph Neural Networks When Meeting HeterophilyCode1
GCNH: A Simple Method For Representation Learning On Heterophilous GraphsCode1
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective DesignsCode1
Geom-GCN: Geometric Graph Convolutional NetworksCode1
Graph Attention NetworksCode1
Graph Neural Networks with Learnable and Optimal Polynomial BasesCode1
Inductive Representation Learning on Large GraphsCode1
Adaptive Universal Generalized PageRank Graph Neural NetworkCode1
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple MethodsCode1
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNsCode1
New Benchmarks for Learning on Non-Homophilous GraphsCode1
Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional NetworksCode0
Show:102550
← PrevPage 1 of 2Next →

No leaderboard results yet.