Thinklab-SJTU / DP3
Deep Point Process by PyTorch
☆28Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for DP3
- Official DGL implementation of "Rethinking High-order Graph Convolutional Networks"☆32Updated 3 years ago
- PyTorch implementation of residual gated graph ConvNets, ICLR’18☆121Updated 6 years ago
- Codes for the paper "Learning Graph-Level Representations with Gated Recurrent Neural Networks"☆29Updated 5 years ago
- Pytorch implementation of the Attention-based Graph Neural Network(AGNN)☆144Updated 6 years ago
- Implementations of "Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks"☆53Updated last month
- AISTATS 2019: Confidence-based Graph Convolutional Networks for Semi-Supervised Learning☆58Updated 5 years ago
- Factoried Neural Relational Inference for Multi-Interacting Systems☆30Updated 5 years ago
- ☆20Updated 4 years ago
- Stochastic training of graph convolutional networks☆85Updated 2 years ago
- Measuring and Improving the Use of Graph Information in Graph Neural Networks☆82Updated 3 months ago
- Learning Steady-States of Iterative Algorithms over Graphs☆40Updated 6 years ago
- informal exposition of Weisfeiler-Leman similarity☆27Updated 3 years ago
- ☆10Updated 2 years ago
- Learning To Stop While Learning To Predict☆33Updated 2 years ago
- ☆15Updated 6 years ago
- Implementation for IGCN and GLP model in our paper "Label Efficient Semi-Supervised Learning via Graph Filtering."☆74Updated 5 years ago
- Codes for NIPS 2019 Paper: Rethinking Kernel Methods for Node Representation Learning on Graphs☆34Updated 4 years ago
- Source code for PairNorm (ICLR 2020)☆76Updated 4 years ago
- Pytorch Implementation of Rethinking Graph Neural Architecture Search from Message-passing (CVPR2021)☆52Updated 2 years ago
- This is a tensorflow implementation of 2018 NIPS paper: [GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations.…☆14Updated 5 years ago
- Generative Matching Networks☆31Updated 7 years ago
- Sparse graph attention☆17Updated 6 years ago
- Code for Graph Neural Networks Exponentially Lose Expressive Power for Node Classification.☆30Updated 4 years ago
- a unified convolution on both Euclidean and non-Euclidean domains☆25Updated 5 years ago
- ☆53Updated 5 years ago
- ☆45Updated 4 years ago
- LSTM implementation, and multi-layer LSTMs for learning on graph neighborhoods☆78Updated 8 years ago