Network Together: Node Classification via Cross network Deep Network Embedding

TL;DR

This paper introduces a novel cross-network deep network embedding model that leverages domain adaptation to learn transferable, label-discriminative node representations across different networks, significantly improving cross-network node classification performance.

Contribution

The paper proposes the CDNE model, integrating domain adaptation into deep network embedding to enable cross-network node classification with network-invariant features.

Findings

CDNE outperforms state-of-the-art methods in cross-network classification

It effectively captures intra-network proximities and cross-network attribute similarities

The model demonstrates strong generalization across different network datasets

Abstract

Network embedding is a highly effective method to learn low-dimensional node vector representations with original network structures being well preserved. However, existing network embedding algorithms are mostly developed for a single network, which fail to learn generalized feature representations across different networks. In this paper, we study a cross-network node classification problem, which aims at leveraging the abundant labeled information from a source network to help classify the unlabeled nodes in a target network. To succeed in such a task, transferable features should be learned for nodes across different networks. To this end, a novel cross-network deep network embedding (CDNE) model is proposed to incorporate domain adaptation into deep network embedding so as to learn label-discriminative and network-invariant node vector representations. On one hand, CDNE leverages network structures to capture the proximities between nodes within a network, by mapping more strongly connected nodes to have more similar latent vector representations. On the other hand, node attributes and labels are leveraged to capture the proximities between nodes across different networks by making the same labeled nodes across networks have aligned latent vector representations. Extensive experiments have been conducted, demonstrating that the proposed CDNE model significantly outperforms the state-of-the-art network embedding algorithms in cross-network node classification.