junhongmit / H2GBLinks
A large-scale node-classification graph benchmark that brings together both the heterophily and heterogeneity properties of real-world graphs. It encompasses 9 real-world datasets spanning 5 diverse domains, 28 baseline models, a new metric, and a unified benchmarking library.
☆37Updated 5 months ago
Alternatives and similar repositories for H2GB
Users that are interested in H2GB are comparing it to the libraries listed below
Sorting:
- ICML 2022, Finding Global Homophily in Graph Neural Networks When Meeting Heterophily☆46Updated 3 years ago
- [IJCAI 2024] Papers about graph reduction including graph coarsening, graph condensation, graph sparsification, graph summarization, etc.☆176Updated this week
- NeurIPS 2022, Revisiting Heterophily For Graph Neural Networks, official PyTorch implementation for Adaptive Channel Mixing (ACM) GNN fra…☆88Updated last year
- A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?☆121Updated 2 years ago
- Pytorch implementation of EvenNet.☆20Updated 3 years ago
- NIPS 24: Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights☆50Updated last year
- The official implementation of the paper "Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing" (ICLR 2023).☆47Updated last year
- Code for GBK-GNN (paper accepted by WWW2022)☆17Updated 3 years ago
- ☆50Updated last year
- ☆38Updated 4 years ago
- Codes for "Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks"☆42Updated 2 years ago
- [Neurips 2024] Disentangled Graph Homophily☆27Updated last year
- A collection of papers on Graph Structural Learning (GSL)☆58Updated 2 years ago
- Resource for "A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective"☆39Updated 8 months ago
- Code for NeurIPS 2022 paper "Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminat…☆56Updated 2 years ago
- [AAAI'23] Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating