Saved in:
Bibliographic Details
Main Authors: 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
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2210.09475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909236913504256
author 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
author_facet 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
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2210_09475
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks
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
Machine Learning
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.
title FIMP: Foundation Model-Informed Message Passing for Graph Neural Networks
topic Machine Learning
url https://arxiv.org/abs/2210.09475