Heterogeneous Graph Neural Network

The source codes for Fine-grained Fact Verification with Kernel Graph Attention Network.

异构图神经网络HAN。Heterogeneous Graph Attention Network (HAN) with pytorch

The GitHub repository for the paper "Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations"

PyTorch implementation of Graph Attention Networks

Course project of SJTU CS3319: Foundations of Data Science, 2023 spring

Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering

IDPS-ESCAPE (Intrusion Detection and Prevention Systems for Evading Supply Chain Attacks and Post-compromise Effects), part of project CyFORT: open-source SOAR system powered by a deep learning-based anomaly detection toolbox (ADBox) and a risk-aware AD-based automated response (RADAR) subsystem integrated with OSS such as Wazuh and Suricata.

Pytorch implementation of graph attention network

Modeling Extent-of-Texture Information for Ground Terrain Recognition

A deep learning library to rank protein complexes using graph neural networks

Detecting Hallucinations in Large Language Model Generations using Graph Structures

Source code accompanying the paper "Reducing Over-smoothing in Graph Neural Networks Using Relational Embeddings" published in DLG-AAAI’23

Keyphrase extraction using graph convolution

Graph Attention Networks for Entity Summarization is the model that applies deep learning on graphs and ensemble learning on entity summarization tasks.

Gated-ViGAT. Code and data for our paper: N. Gkalelis, D. Daskalakis, V. Mezaris, "Gated-ViGAT: Efficient bottom-up event recognition and explanation using a new frame selection policy and gating mechanism", IEEE International Symposium on Multimedia (ISM), Naples, Italy, Dec. 2022.

Implementation of the spatialGAT in the paper: Spatial Attention Based Grid Representation Learning for Predicting Origin–Destination Flow (IEEE Big Data 2022)

This repository hosts the scripts and some of the pre-trained models presented in out paper "ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network", IEEE Access, 2022.

Heterogenous Graph Attention Transformer for high-resolution, distributed spatiotemporal flood prediction. Published at ACM SIGSPATIAL 2025.

Dense and Sparse Implementation of GAT written by PyTorch