Abstract: Graph spectral filtering relies on a representation matrix to define the frequency-domain transformations. Conventional approaches use fixed graph representations, which limit their ...

Abstract: Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental operation in graph computing and analytics. However, the irregularity of real-world graphs poses significant challenges to ...

We developed multi-label incremental learning code based on the PyCIL toolkit. Reference details are in Section B.2 of the paper. Users can still extend other methods in PyCIL to multi-label scenarios ...

A powerful AI agent system that combines traditional RAG (Retrieval-Augmented Generation) with knowledge graph capabilities to analyze and provide insights about big tech companies and their AI ...