Buchumschlag

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rizvi, Syed Asad, Pallikkavaliyaveetil, Nazreen, Zhang, David, Lyu, Zhuoyang, Nguyen, Nhi, Lyu, Haoran, Christensen, Benjamin, Caro, Josue Ortega, Fonseca, Antonio H. O., Zappala, Emanuele, Bagherian, Maryam, Averill, Christopher, Abdallah, Chadi G., Karbasi, Amin, Ying, Rex, Brbic, Maria, Dhodapkar, Rahul Madhav, van Dijk, David
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Machine Learning
Online-Zugang:https://arxiv.org/abs/2210.09475
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Inhaltsangabe:
  • Foundation models have achieved remarkable success across many domains, relying on pretraining over vast amounts of data. Graph-structured data often lacks the same scale as unstructured data, making the development of graph foundation models challenging. In this work, we propose Foundation-Informed Message Passing (FIMP), a Graph Neural Network (GNN) message-passing framework that leverages pretrained non-textual foundation models in graph-based tasks. We show that the self-attention layers of foundation models can effectively be repurposed on graphs to perform cross-node attention-based message-passing. Our model is evaluated on a real-world image network dataset and two biological applications (single-cell RNA sequencing data and fMRI brain activity recordings) in both finetuned and zero-shot settings. FIMP outperforms strong baselines, demonstrating that it can effectively leverage state-of-the-art foundation models in graph tasks.

Ähnliche Einträge