GraphNeuralRAG: On the Opportunities and Challenges of GNNs for GraphRAG, from Multi-Hop Question Answering to Perturbation Modelling

Add to your list(s) Download to your calendar using vCal

• Andrea Giuseppe Di Francesco, Sapienza University of Rome, ISTI-CNR
• Thursday 09 April 2026, 15:00-16:00
• Computer Laboratory, William Gates Building, Room LT1.

If you have a question about this talk, please contact Pietro Lio.

Google meet's link: https://meet.google.com/ypo-yqjc-cwv

Retrieval-augmented generation (RAG) has become the standard approach for grounding generative models in external knowledge. When that knowledge is structured as a graph, GraphRAG methods have emerged to leverage topology to boost retrieval. However, existing approaches predominantly rely on either LLM -based pipelines, which treat graph structure as text to summarise or traverse, or use graph algorithms and neural scoring only as an intermediate step before falling back to document-based retrieval, leaving much of the graph structure unexploited by the generative model. Graph Neural Networks (GNNs) offer a compelling middle ground: natively designed for graph-structured data, learnable end-to-end, and capable of encoding complex relational patterns into compact representations. This talk explores the opportunities and challenges of placing GNNs at the core of GraphRAG pipelines, presenting a GraphNeuralRAG framework across two domains. In multi-hop question answering over knowledge graphs, GNN -based retrieval is shown to address key limitations of document-centric approaches, including recall-precision tradeoffs, token inefficiency, and loss of structural information. In perturbation modelling, PT-RAG (ICLR 2026 Workshop on Generative AI in Genomics) is presented as the first RAG framework for predicting single-cell responses to gene perturbations, followed by a discussion of how gene-gene networks provide a natural graph substrate for extending this into a full GraphNeuralRAG pipeline. The focus throughout is on both what GNNs uniquely enable and what remains hard, offering an honest map of this emerging research direction.

This talk is part of the Foundation AI series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Computer Laboratory, William Gates Building, Room LT1
• Department of Computer Science and Technology talks and seminars
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• Martin's interesting talks
• PhD related
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list
• yk449

Note that ex-directory lists are not shown.