Representation learning on dynamic graphs using self-attention networks

Variational Graph Recurrent Neural Networks - PyTorch

CTGCN: k-core based Temporal Graph Convolutional Network for Dynamic Graphs (accepted by IEEE TKDE in 2020) https://ieeexplore.ieee.org/document/9240056

Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features

[AAAI 2023] Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks

[ACM Computing Surveys'23] Implementations or refactor of some temporal link prediction/dynamic link prediction methods and summary of related open resources for survey paper "Temporal Link Prediction: A Unified Framework, Taxonomy, and Review" which has been accepted by ACM Computing Surveys.

[NeurIPS 2022] The official PyTorch implementation of "Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs"

[ICDM 2020] Python implementation for "Dynamic Graph Collaborative Filtering."

Code for "Graph Neural Networks for Friend Ranking in Large-scale Social Platforms" (WWW 2021).

The official repository for the paper "Deep learning for dynamic graphs: models and benchmarks" accepted at IEEE TNNLS

Official reference implementation of our paper "Temporal Graph ODEs for Irregularly-Sampled Time Series" accepted at IJCAI 24

Implementation codes for KDD24 paper "LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?"

DYnamic MOtif-NoDes (DYMOND) is a dynamic network generative model based on temporal motifs and node behavior.

Python 3 supported version for DySAT

Representation and learning framework for dynamic graphs using Graph Neural Networks.

dynnode2vec is a python package that implements algorithms to embed dynamic graphs

Implementation codes for NeurIPS23 paper "Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts"

[TKDE'23] Demo code of the paper entitled "High-Quality Temporal Link Prediction for Weighted Dynamic Graphs via Inductive Embedding Aggregation", which has been accepted by IEEE TKDE

Official reference implementation of our paper "Long Range Propagation on Continuous-Time Dynamic Graphs" accepted at ICML24 and "Effective Non-Dissipative Propagation for Continuous-Time Dynamic Graphs" accepted at Temporal Graph Learning Workshop @ NeurIPS 2023

The code for our ICLR 2024 paper: "Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs"