gnn-pytorch

GNN方法和模型的Pytorch实现。Pytorch implementation of GNN.

A PyG-based package of spectral GNNs with benchmark evaluations (SIGMOD 2026).

This project detects Pneumonia from Chest X-ray images using deep learning. It explores four approaches: A custom CNN built from scratch ResNet with transfer learning Graph Neural Network (GAT) for spatial reasoning A Multimodal model combining global and patch features The dataset used is from Kaggle's Chest X-Ray Pneumonia collection.

Graph-Based Reinforcement Learning for Structural Cross-Sectional Design Optimization

This repository provides supplementary dataset and code of TDHCNMDA.

Spatio-Temporal GNN (T-GCN, A3T-GCN) for stock trend classification and price forecasting for portfolio selection.

Implementation in Pytorch of the article "E(n) Equivariant Graph Neural Network" - Satorras et al.

Reproducible Optimal PMU Placement (OPP) framework using a Graph Neural Network trained on solutions generated by a greedy OPP method.

WIP Bidirectional RGAT for multistage incident classification, prioritization, and an addition to automation processes through a bidirectional R-GAT; the graphs are built using events as nodes, mitigating overfitting risks of entity based nodes. The project is learning by doing approach to understanding its potential and limitations

蔡老師的課程作業

Master's Thesis developed at Technische Universität München (TUM) under supervision of Prof. Stephan Günnemann.

Introduction to applied machine learning