Year: 2020
Type: article
Abstract: Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in thecompletely-imbalancedlabel setting where some classes have no labeled nodes at all. To alleviate this, we propose two novel semi-supervised network embedding methods. The first one is a shallow method named RSDNE. Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. The other method is RECT which is a new class of graph neural networks. Different from RSDNE, to benefit from the completely-imbalanced labels, RECT explores the class-semantic knowledge. This enables RECT to handle networks with node features and multi-label setting. Experimental results on several real-world datasets demonstrate the superiority of the proposed methods.
Authors: Zheng Wang, Xiaojun Ye, Chaokun Wang, Jian Cui, Philip S. Yu
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: III: Small: Exploiting the Massive User Generated Utterances for Intent Mining under Scarce Annotations, G2968912209, III: Medium: Collaborative Research: An Extensible Heterogeneous Network Embedding Framework with Application Specific Adaptation, 复杂条件社区发现关键技术研究, G4579724647, G6835984654, III: Small: Fusion of Heterogeneous Networks for Synergistic Knowledge Discovery, SaTC: CORE: Small: Collaborative: Learning Dynamic and Robust Defenses Against Co-Adaptive Spammers
OpenAlex ID: W3005050348