Collective Link Prediction Oriented Network Embedding with Hierarchical Graph Attention

TL;DR

This paper introduces HGANE, a hierarchical graph attention network that improves collective link prediction across multiple aligned social networks by effectively handling network differences and link directions.

Contribution

The paper proposes a novel application-oriented network embedding framework with hierarchical attention for collective link prediction in directed aligned networks, addressing network heterogeneity and link directionality.

Findings

HGANE outperforms state-of-the-art methods in real-world datasets.

The hierarchical attention mechanism effectively handles network differences.

The model significantly improves collective link prediction accuracy.

Abstract

To enjoy more social network services, users nowadays are usually involved in multiple online sites at the same time. Aligned social networks provide more information to alleviate the problem of data insufficiency. In this paper, we target on the collective link prediction problem and aim to predict both the intra-network social links as well as the inter-network anchor links across multiple aligned social networks. It is not an easy task, and the major challenges involve the network characteristic difference problem and different directivity properties of the social and anchor links to be predicted. To address the problem, we propose an application oriented network embedding framework, Hierarchical Graph Attention based Network Embedding (HGANE), for collective link prediction over directed aligned networks. Very different from the conventional general network embedding models, HGANE effectively incorporates the collective link prediction task objectives into consideration. It learns the representations of nodes by aggregating information from both the intra-network neighbors (connected by social links) and inter-network partners (connected by anchor links). What's more, we introduce a hierarchical graph attention mechanism for the intra-network neighbors and inter-network partners respectively, which resolves the network characteristic differences and the link directivity challenges effectively. Extensive experiments have been conducted on real-world aligned networks datasets to demonstrate that our model outperformed the state-of-the-art baseline methods in addressing the collective link prediction problem by a large margin.