guoji-fu / GSDN
The source code of the paper "Understanding Graph Neural Networks from Graph Signal Denoising Perspectives"
☆23Updated 4 years ago
Alternatives and similar repositories for GSDN:
Users that are interested in GSDN are comparing it to the libraries listed below
- ☆12Updated 4 years ago
- ☆17Updated 2 years ago
- Gromov-Wasserstein Factorization Models for Graph Clustering (AAAI-20)☆31Updated 2 years ago
- Codes for NIPS 2019 Paper: Rethinking Kernel Methods for Node Representation Learning on Graphs☆34Updated 5 years ago
- ☆16Updated 4 years ago
- Variational Graph Convolutional Networks☆22Updated 4 years ago
- Rethinking Graph Regularization for Graph Neural Networks (AAAI2021)☆34Updated 3 years ago
- The PyTorch implementation of Directed Graph Contrastive Learning (DiGCL), NeurIPS-2021☆36Updated 3 years ago
- code for the paper in NeurIPS 2019☆40Updated 2 years ago
- Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization (NeurIPS 21')☆23Updated 3 years ago
- Reference implementation of the HEAT algorithm described in https://link.springer.com/chapter/10.1007/978-3-030-62362-3_4☆11Updated 2 years ago
- Scattering GCN: overcoming oversmoothness in graph convolutional networks☆25Updated 2 years ago
- Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport☆36Updated 4 years ago
- Official Code of Decoupled Graph Convolution (DGC)☆16Updated 3 years ago
- [CVPR 2020] L2-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks☆30Updated 3 years ago
- PyTorch Codes for Haar Graph Pooling☆11Updated 2 years ago
- First and Complementary Neighborhood Combination of Adjacency Matrix for Graph Learning☆20Updated last year
- NeurIPS 2022: Tree Mover’s Distance: Bridging Graph Metrics and Stability of Graph Neural Networks☆36Updated last year
- Graph Transformers for Large Graphs☆21Updated 11 months ago
- ☆35Updated 5 years ago
- ☆27Updated 3 years ago
- The implementation code for our paper Wasserstein Embedding for Graph Learning (ICLR 2021).☆34Updated 4 years ago
- Code for Graph Neural Networks Exponentially Lose Expressive Power for Node Classification.☆30Updated 4 years ago
- Equivalence Between Structural Representations and Positional Node Embeddings☆21Updated 5 years ago
- Code for reproducing results in GraphMix paper☆72Updated 2 years ago
- ☆10Updated 5 years ago
- ☆30Updated 2 years ago
- The implementation of our AAAI 2020 paper "GSSNN: Graph Smoothing Splines Neural Network".☆20Updated 4 years ago
- A PyTorch implementation of "SelfGNN: Self-supervised Graph Neural Networks without explicit negative sampling" paper, which appeared in …☆30Updated 3 years ago
- Gromov-Wasserstein Learning for Graph Matching and Node Embedding☆72Updated 5 years ago