Hyper-Path-Based Representation Learning for Hyper-Networks

TL;DR

This paper introduces a novel hyper-path-based approach for learning representations in hyper-networks, effectively capturing complex tuplewise relationships and addressing the limitations of traditional pairwise methods.

Contribution

It defines a new metric for hyper-network indecomposability, proposes hyper-paths and a hyper-gram algorithm to preserve structural information, and demonstrates superior performance on real-world tasks.

Findings

Effective in capturing tuplewise relationships

Outperforms existing models in link prediction

Validates on multiple real-world datasets

Abstract

Network representation learning has aroused widespread interests in recent years. While most of the existing methods deal with edges as pairwise relationships, only a few studies have been proposed for hyper-networks to capture more complicated tuplewise relationships among multiple nodes. A hyper-network is a network where each edge, called hyperedge, connects an arbitrary number of nodes. Different from conventional networks, hyper-networks have certain degrees of indecomposability such that the nodes in a subset of a hyperedge may not possess a strong relationship. That is the main reason why traditional algorithms fail in learning representations in hyper-networks by simply decomposing hyperedges into pairwise relationships. In this paper, we firstly define a metric to depict the degrees of indecomposability for hyper-networks. Then we propose a new concept called hyper-path and design hyper-path-based random walks to preserve the structural information of hyper-networks according to the analysis of the indecomposability. Then a carefully designed algorithm, Hyper-gram, utilizes these random walks to capture both pairwise relationships and tuplewise relationships in the whole hyper-networks. Finally, we conduct extensive experiments on several real-world datasets covering the tasks of link prediction and hyper-network reconstruction, and results demonstrate the rationality, validity, and effectiveness of our methods compared with those existing state-of-the-art models designed for conventional networks or hyper-networks.