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 11–20 of 29 papers

TitleStatusHype
Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing PatternsCode1
New Benchmarks for Learning on Non-Homophilous GraphsCode1
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural NetworksCode1
Beyond Low-frequency Information in Graph Convolutional NetworksCode1
Combining Label Propagation and Simple Models Out-performs Graph Neural NetworksCode1
Simple and Deep Graph Convolutional NetworksCode1
Beyond Homophily in Graph Neural Networks: Current Limitations and Effective DesignsCode1
Adaptive Universal Generalized PageRank Graph Neural NetworkCode1
Non-Local Graph Neural NetworksCode1
Geom-GCN: Geometric Graph Convolutional NetworksCode1
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.