Associative Learning for Network Embedding

TL;DR

This paper introduces a novel network embedding approach using Modern Hopfield Networks for associative learning, capturing node-neighbor relationships to improve downstream task performance.

Contribution

It proposes a new method leveraging MHNs for network embedding, focusing on associative learning rather than matrix factorization or deep learning.

Findings

Competitive performance on node classification

Effective in linkage prediction tasks

Outperforms some traditional embedding methods

Abstract

The network embedding task is to represent the node in the 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 downstream tasks such as node classification and linkage prediction. The results show competitive performance compared to the common matrix factorization techniques and deep learning based methods.