Modern Hopfield Networks for graph embedding
Name
fdata-05-1044709.pdf
Description
Published version
Size
1016.01 KB
Format
Adobe PDF
Checksum (MD5)
d7117ca38080c09d5732b782fb4ac6e2
Author(s)
Liang, Yuchen
Krotov, Dmitry
Zaki, Mohammed J
Date Issued
November 17, 2022
Journal
Frontiers in Big Data
Publisher
Frontiers Media SA
Citation
Liang Y, Krotov D and Zaki MJ (2022) Modern Hopfield Networks for graph embedding. Front. Big Data 5:1044709.
Version
Final published version
Abstract
The network embedding task is to represent a node in a network as a low-dimensional vector while incorporating the topological and structural information. Most existing approaches solve this problem by factorizing a proximity matrix, either directly or implicitly. In this work, we introduce a network embedding method from a new perspective, which leverages Modern Hopfield Networks (MHN) for associative learning. Our network learns associations between the content of each node and that node's neighbors. These associations serve as memories in the MHN. The recurrent dynamics of the network make it possible to recover the masked node, given that node's neighbors. Our proposed method is evaluated on different benchmark datasets for downstream tasks such as node classification, link prediction, and graph coarsening. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.
MIT Department
MIT-IBM Watson AI Lab
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.3389/fdata.2022.1044709
