IEEE

A Flexible Diffusion Convolution for Graph Neural Networks

Abstract: Graph Neural Networks (GNNs) have been gaining more attention due to their excellent performance in modeling various graph-structured data. However, most of the current GNNs only consider ...
IEEE

An Adaptive Framework Embedded With LLM for Knowledge Graph Construction

Abstract: Knowledge graph construction is aimed at storing and representing the knowledge of the objective world in a structured form. Existing methods for automatic construction of knowledge graphs ...
GitHub

Generative Graph Pattern Machine (G2PM)

This is the official implementation of our paper Scalable Graph Generative Modeling via Substructure Sequences, a self-supervised extension of our ICML'25 work GPM. G2PM addresses the fundamental ...
GitHub

AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection

1️⃣ AnomalyGFM is the first GAD-oriented GFM with strong zero-shot and few-shot generalization abilities. 2️⃣ AnomalyGFM is pre-trained to learn discriminative, graph-agnostic class prototypes with ...