kedar2 / FoSRLinks
FoSR: First-order spectral rewiring for addressing oversquashing in GNNs
☆9Updated 2 years ago
Alternatives and similar repositories for FoSR
Users that are interested in FoSR are comparing it to the libraries listed below
Sorting:
- Main code for "Revisiting over-smoothing and over-squashing using the Ollivier-Ricci curvature" paper☆17Updated 2 years ago
- Official repository for On Over-Squashing in Message Passing Neural Networks (ICML 2023)☆15Updated last year
- ☆16Updated 7 months ago
- A Note On Over-Smoothing for Graph Neural Network☆20Updated 5 years ago
- 🐼PANDA: Expanded Width-Aware Message Passing Beyond Rewiring, ICML 2024☆20Updated 10 months ago
- Temporal Graph Rewiring Method with Expander Graphs☆12Updated 8 months ago
- Gradient gating (ICLR 2023)☆53Updated 2 years ago
- ☆18Updated last year
- Code for AAAI21 paper "Scalable and Explainable 1-Bit Matrix Completion via Graph Signal Learning"☆11Updated 3 years ago
- ☆12Updated last year
- Graph Neural Convection-Diffusion with Heterophily☆11Updated 2 years ago
- [ICLR'25 Spotlight] Revisiting Random Walks for Learning on Graphs (RWNN), in PyTorch☆13Updated 4 months ago
- ☆31Updated last year
- This repo contains a reference implementation for the paper "Breaking the Limit of Graph Neural Networks by Improving the Assortativity o…☆32Updated 3 years ago
- Code repository of "Towards Deep Attention in Graph Neural Networks: Problems and Remedies," published in ICML 2023.☆29Updated 3 months ago
- ☆40Updated 3 years ago
- Uncertainty Quantification over Graph with Conformalized Graph Neural Networks (NeurIPS 2023)☆83Updated last year
- Code of "Analyzing the Expressive Power of Graph Neural Networks in a Spectral Perspective" paper published in ICLR2021☆46Updated 4 years ago
- ☆21Updated last year
- Implementation of the paper "A New Perspective on the Effects of Spectrum in Graph Neural Networks"☆17Updated 3 years ago
- Codes for "Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks"☆38Updated 2 years ago
- CAT-Walk is an inducive method that learns hyperedge representations via a novel higher-order random walk, SetWalk.☆15Updated last year
- This is the code of paper: Robust Mid-Pass Filtering Graph Convolutional Networks.(paper accepted by WWW2023)☆13Updated 2 years ago
- Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products (ICML 2024)☆9Updated last year
- The official source code for "S-Mixup: Structural Mixup for Graph Neural Networks", accepted at CIKM 2023 (Short Paper).☆18Updated last year
- Code for our paper "Attending to Graph Transformers"☆89Updated last year
- Official code implementation for WSDM 23 paper Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs.☆34Updated 2 years ago
- GREAD: Graph Neural Reaction-Diffusion Networks, ICML 2023☆58Updated last year
- Official implementation for paper: Probabilistically Rewired Message-Passing Neural Networks, accepted at ICLR 2024.☆21Updated 5 months ago
- Official Implementation of Half-Hop☆19Updated last year