Structural Deep Embedding for Hyper-Networks

TL;DR

This paper introduces a novel deep embedding model for hyper-networks with indecomposable hyperedges, addressing limitations of existing methods and demonstrating superior performance across diverse real-world hyper-networks.

Contribution

The paper proposes a new deep hyper-network embedding model that preserves indecomposability and non-linear similarities, advancing hyper-network analysis.

Findings

Outperforms state-of-the-art algorithms on four hyper-network datasets.

Theoretically proves limitations of linear similarity metrics in hyper-networks.

Effectively preserves local and global proximities in embeddings.

Abstract

Network embedding has recently attracted lots of attentions in data mining. Existing network embedding methods mainly focus on networks with pairwise relationships. In real world, however, the relationships among data points could go beyond pairwise, i.e., three or more objects are involved in each relationship represented by a hyperedge, thus forming hyper-networks. These hyper-networks pose great challenges to existing network embedding methods when the hyperedges are indecomposable, that is to say, any subset of nodes in a hyperedge cannot form another hyperedge. These indecomposable hyperedges are especially common in heterogeneous networks. In this paper, we propose a novel Deep Hyper-Network Embedding (DHNE) model to embed hyper-networks with indecomposable hyperedges. More specifically, we theoretically prove that any linear similarity metric in embedding space commonly used in existing methods cannot maintain the indecomposibility property in hyper-networks, and thus propose a new deep model to realize a non-linear tuplewise similarity function while preserving both local and global proximities in the formed embedding space. We conduct extensive experiments on four different types of hyper-networks, including a GPS network, an online social network, a drug network and a semantic network. The empirical results demonstrate that our method can significantly and consistently outperform the state-of-the-art algorithms.