G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding | Xiaoxin He

Portal is the home of the AI for drug discovery community. Join for more details on this talk and to connect with the speakers: https://portal.valencelabs.com/logg

Given a graph with textual attributes, we enable users to `chat with their graph': that is, to ask questions about the graph using a conversational interface. In response to a user's questions, our method provides textual replies and highlights the relevant parts of the graph. While existing works integrate large language models (LLMs) and graph neural networks (GNNs) in various ways, they mostly focus on either conventional graph tasks (such as node, edge, and graph classification), or on answering simple graph queries on small or synthetic graphs. In contrast, we develop a flexible question-answering framework targeting real-world textual graphs, applicable to multiple applications including scene graph understanding, common sense reasoning, and knowledge graph reasoning. Toward this goal, we first develop a Graph Question Answering (GraphQA) benchmark with data collected from different tasks. Then, we propose our G-Retriever method, introducing the first retrieval-augmented generation (RAG) approach for general textual graphs, which can be fine-tuned to enhance graph understanding via soft prompting. To resist hallucination and to allow for textual graphs that greatly exceed the LLM's context window size, G-Retriever performs RAG over a graph by formulating this task as a Prize-Collecting Steiner Tree optimization problem. Empirical evaluations show that our method outperforms baselines on textual graph tasks from multiple domains, scales well with larger graph sizes, and mitigates hallucination.~\footnote{Our codes and datasets are available at: \url{this https URL}}

Paper link: https://arxiv.org/abs/2402.07630

Speakers: Xiaoxin He

Twitter Hannes:   / hannesstaerk  
Twitter Dominique:   / dom_beaini  

~

Chapters
00:00 - Intro + Background
08:08 - Review of Graphs and LLMs
20:29 - G-Retriever
43:26 - Conclusion
46:22 - Future Directions
48:38 - Q+A