This is the PyTorch implementation for LightGCL proposed in the paper LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation, International Conference on Learning Representation, ...

Abstract: Recent advancements in learning from graph-structured data have highlighted the importance of graph convolutional networks (GCNs). Despite some research efforts on the theoretical aspects of ...

This repository contains the source code of TopoNet, Graph-based Topology Reasoning for Driving Scenes. TopoNet is the first end-to-end framework capable of abstracting traffic knowledge beyond ...

Abstract: A new systems description method that utilizes graph theory for systems modeling is presented. The new method represents the system in terms of a directed graph, where each system component ...