Combining GNNs and LLMs for Advanced Reasoning
Summary
Integrates implicit knowledge of pre-trained LLMs with structural reasoning capabilities of Graph Neural Networks for novel multi-modal AI models. Applications span health sciences, logistics, 5G/6G networks, and data analytics. Targets intent-based optimization, question answering grounded in knowledge graphs.
Themes
Keywords
GNN, LLM, knowledge graphs, multi-modal, reasoning