gatv2

Code for the paper "How Attentive are Graph Attention Networks?" (ICLR'2022)

B站GNN教程资料

Comparative Analysis of Graph Neural Networks for Node Regression task on Wiki-Squirrel dataset (Bachelor's Research Project)

Empirical Research over the possible advantages of pretraining a Graph Neural Network for Classification by using Link Prediction. We used GCN, GAT and GraphSAGE with minibatch generation. Done for the Learning From Networks course taught by professor Fabio Vandin at the University of Padova

AI-powered pharmacogenomics platform using GATv2 to predict organ health, drug interactions, and personalized longevity insights from DNA, lifestyle, and medications.

A robust Neuro-Symbolic Sudoku Solver combining Graph Attention Networks (GATv2) with Dynamic Constraint Propagation. Efficiently solves NP-hard puzzles where traditional backtracking fails

Graph neural networks for corporate fraud detection: a leakage-controlled evaluation of representation and structure. UCL MSc dissertation (IFTE0008).

A web application for extractive summarization

This repository contains the implementation of some of the popular Graph Neural Networks (GNNs) using PyTorch Geometric to solve node classification tasks.

This repository presents and compares HeterSUMGraph and variants using GATConv, GATv2Conv and a combination of HeterSUMGraph and SummaRuNNer (using HeterSUMGraph as a sentence encoder).

Dual-mode flood and drought cascade forecasting on a block-level graph · GATv2+GRU · GNN-LRP walk explanations · CP-SAT allocation · IndicTrans2 alerts

This repository presents and compares HeterSUMGraph and variants doing extractive summarization, named entity recognition or both. HeterSUMGraph and variants use GATv2Conv (from torch_geometric).

This repository classifies nodes and graphs and predicts links using PyG, covering data processing, model building, and testing

Leveraging advanced graph neural networks to enhance the classification of bladder cancer subtypes by integrating multi-omics data