From graph theory to graph neural networks (GNNs): The opportunities of GNNs in power electronics

Y Li, C Xue, F Zargari, YR Li - IEEE Access, 2023 - ieeexplore.ieee.org
Graph theory within power electronics, developed over a 50-year span, is continually
evolving, necessitating ongoing research endeavors. Facing with the never-been-seen …

Can llms effectively leverage graph structural information: when and why

J Huang, X Zhang, Q Mei, J Ma - 2023 - openreview.net
This paper studies Large Language Models (LLMs) augmented with structured data--
particularly graphs--a crucial data modality that remains underexplored in the LLM literature …

Can llms effectively leverage graph structural information through prompts, and why?

J Huang, X Zhang, Q Mei, J Ma - arxiv preprint arxiv:2309.16595, 2023 - arxiv.org
Large language models (LLMs) are gaining increasing attention for their capability to
process graphs with rich text attributes, especially in a zero-shot fashion. Recent studies …

A metadata-driven approach to understand graph neural networks

TW Li, Q Mei, J Ma - Advances in Neural Information …, 2023 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) have achieved remarkable success in various
applications, but their performance can be sensitive to specific data properties of the graph …