Network Together: Node Classification via Cross network Deep Network Embedding

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.

Codes and Datasets are available at https://github.com/shenxiaocam/CDNE. Please cite our paper as: X. Shen, Q. Dai, S. Mao, F. Chung and K. Choi, "Network Together: Node Classification via Cross-Network Deep Network Embedding," in IEEE Transactions on Neural Networks and Learning Systems, early access, Jun. 4, 2020

References in corpus (5)

• LINE: Large-scale Information Network Embedding
• Inductive Representation Learning on Large Graphs
• REGAL: Representation Learning-based Graph Alignment
• Deep Transfer Network: Unsupervised Domain Adaptation
• Deep Network Embedding for Graph Representation Learning in Signed Networks

Cited by in corpus (10)

• Domain-adaptive Message Passing Graph Neural Network
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
• Network Alignment
• Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
• Graph Domain Adaptation: Challenges, Progress and Prospects
• Source Free Unsupervised Graph Domain Adaptation
• Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Adversarial Deep Network Embedding for Cross-network Node Classification
• Unveiling Class-Labeling Structure for Universal Domain Adaptation