Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

TL;DR

This paper introduces a novel framework using pseudo anchors and meta-learning to improve embedding-based social network alignment, especially effective with limited labeled data.

Contribution

It proposes a new learning approach that enforces wider separation of user embeddings via pseudo anchors and meta-learning, applicable across various models.

Findings

Pseudo anchors significantly improve alignment accuracy.

The framework outperforms baseline models with fewer labeled anchors.

Effective across multiple state-of-the-art models.

Abstract

Social network alignment aims at aligning person identities across social networks. Embedding based models have been shown effective for the alignment where the structural proximity preserving objective is typically adopted for the model training. With the observation that ``overly-close'' user embeddings are unavoidable for such models causing alignment inaccuracy, we propose a novel learning framework which tries to enforce the resulting embeddings to be more widely apart among the users via the introduction of carefully implanted pseudo anchors. We further proposed a meta-learning algorithm to guide the updating of the pseudo anchor embeddings during the learning process. The proposed intervention via the use of pseudo anchors and meta-learning allows the learning framework to be applicable to a wide spectrum of network alignment methods. We have incorporated the proposed learning framework into several state-of-the-art models. Our experimental results demonstrate its efficacy where the methods with the pseudo anchors implanted can outperform their counterparts without pseudo anchors by a fairly large margin, especially when there only exist very few labeled anchors.