Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This repository contains the resources on graph neural network (GNN) considering heterophily.
| Date | Stars |
|---|---|
| 2026-07-31 | 273 |
| 2026-08-06 | 273 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Resources on Graph Neural Networks With Heterophily This repository contains the relevant resources on graph neural network (GNN) considering heterophily. It's worth noting that the **heterophily** we consider here is not the same as **heterogeneity**. Heterogeneity is more related to the node type difference such as the user and item nodes in recommender systems, but heterophily is more like the feature or label difference between the neighbors under the nodes with the same type. Traditional GNNs usually assume that similar nodes (features/classes) are connected together, but the "opposites attract" phenomenon also widely exists in general graphs. If you find anything incorrect, please let me know. Thanks! <!--[[Paper](https://arxiv.org/abs/2101.00797)], [[Code](https://github.com/bdy9527/FAGCN)]--> <!-- [[Paper]()], [[Code]()] --> <!-- [[Paper]()], [Code] --> ## Papers ### 2024 - Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks, NeurIPS, [[Paper](https://arxiv.org/abs/2404.03139)], [Code] - Spectral Graph Pruning Against Over-Squashing and Over-Smoothing, NeurIPS, [[Paper](https://arxiv.org/abs/2404.04612)], [Code] - Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections, NeurIPS, [[Paper](https://arxiv.org/abs/2406.03052)], [[Code](https://github.com/CGCL-codes/NIFA)] - Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification, NeurIPS, [[Paper](https://arxiv.org/abs/2410.16845)], [[Code](https://github.com/draym28/FGSAM_NeurIPS24)] - On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks, NeurIPS, [[Paper](https://arxiv.org/abs/2409.17475)], [Code] - Graph as a feature: improving node classification with non-neural graph-aware logistic regression, arXiv, [[Paper](https://arxiv.org/abs/2411.12330)], [[Code](https://github.com/graph-lr/graph-aware-logistic-regression)] - Heterophilic Graph Neural Networks Optimization with Causal Message-passing, arXiv, [[Paper](https://arxiv.org/abs/2411.13821)], [Code] - GrokFormer: Graph Fourier Kolmogorov-Arnold Transformers, arXiv, [[Paper](https://arxiv.org/abs/2411.17296)], [[Code](https://github.com/GGA23/GrokFormer)] - Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs, arXiv, [[Paper](https://arxiv.org/abs/2411.11284)], [Code] - DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling, arXiv, [[Paper](https://arxiv.org/abs/2409.19616)], [[Code](https://github.com/basiralab/DuoGNN)] - ScaleNet: Scale Invariance Learning in Directed Graphs, arXiv, [[Paper](https://arxiv.org/abs/2411.08758)], [[Code](https://github.com/Qin87/ScaleNet/tree/July25)] - Is Graph Convolution Always Beneficial For Every Feature?, arXiv, [[Paper](https://arxiv.org/abs/2411.07663)], [Code] - Rethinking Structure Learning For Graph Neural Networks, arXiv, [[Paper](https://arxiv.org/abs/2411.07672)], [Code] - Unveiling the Impact of Local Homophily on GNN Fairness: In-Depth Analysis and New Benchmarks, arXiv, [[Paper](https://arxiv.org/abs/2410.04287)], [Code] - SiMilarity-Enhanced Homophily for Multi-View Heterophilous Graph Clustering, arXiv, [[Paper](https://arxiv.org/abs/2410.03596)], [Code] - Dual-Optimized Adaptive Graph Reconstruction for Multi-View Graph Clustering, ACM MM, [[Paper](https://arxiv.org/abs/2410.22983)], [Code] - Graph Neural Networks with Feature and Structure Aware Random Walk, arXiv, [[Paper](https://arxiv.org/abs/2111.10102)], [[Code](https://anonymous.4open.science/r/DiLGCN-CT)] - Learning Graph Quantized Tokenizers for Transformers, arXiv, [[Paper](https://arxiv.org/abs/2410.13798)], [[Code](https://github.com/limei0307/graph-tokenizer)] - Addressing Heterogeneity and Heterophily in Graphs: A Heterogeneous Heterophilic Spectral Graph Neural Network, arXiv, [[Paper](https://arxiv.org/abs/2410.13373)], [Code] - Perseus: Leveraging Common
Excerpt of 53,233 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:8aea6b75f5f6eb14, llm:Repository topics and description: 'graph-neural-networks', 'heterophily', 'graph-data', 'datasets' and description: 'resources on graph neural network (GNN) considering heterophily.'
matched fp:8aea6b75f5f6eb14, llm:Repository topics and description: 'graph-neural-networks', 'heterophily', 'graph-data', 'datasets' and description: 'resources on graph neural network (GNN) considering heterophily.'
matched fp:8aea6b75f5f6eb14, llm:Repository topics and description: 'graph-neural-networks', 'heterophily', 'graph-data', 'datasets' and description: 'resources on graph neural network (GNN) considering heterophily.'