This repository is used to collect papers and code in the field of AI.

PyGDA is a Python library for Graph Domain Adaptation.

Collection of Machine Learning and GNN methods for Molecular Property Prediction Task

Exercises on Machine Learning

WholeGraph - large scale Graph Neural Networks

The PyTorch implementation of STGCN.

A Comprehensive Survey of Mamba in Deep Learning

The official source code of the paper "Unsupervised Episode Generation for Graph Meta-learning" (to be presented in ICML 2024)

[ICLR 2024] Official implementation of the paper "GNNBoundary"

[ICLR 2023] Official implementation of the paper "GNNInterpreter"

DiTEC research

PyTorch implementation of GNN models

Reconstruct billions of particle trajectories with graph neural networks

Holistic understanding of Large Language Models (LLMs) involves integrating NLP, computer vision, audio processing, and reinforcement learning. GNNs capture intricate data relationships. Attention mechanisms, Transformer architectures, vision-language pre-training, audio processing with spectrograms, pre-trained embeddings, and reinforcement .

Molecular substructure graph attention network for molecular property identification in drug discovery. This is the starting point for my thesis project and is the fork of a repository from the paper https://doi.org/10.1016/j.patcog.2022.108659

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

GSCAN: Graph Stability Clustering using Edge-Aware Excess-of-Mass

DeepONets, (Fourier) Neural Operators, Physics-Informed Neural Operators, and more in Julia

Evaluating the generalizability of graph neural networks for predicting collision cross section

NeuroGNN is a state-of-the-art framework for precise seizure detection and classification from EEG data. It employs dynamic Graph Neural Networks (GNNs) to capture intricate spatial, temporal, semantic, and taxonomic correlations between EEG electrode locations and brain regions, resulting in improved accuracy. Presented at PAKDD '24.