Locality-aware tail node embeddings on homogeneous and heterogeneous networks

• Main Authors: LIU, Zemin, FANG, Yuan, ZHANG, Wentao, ZHANG, Xinming, HOI, Steven C. H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Adaptation models; Encyclopedias; Heterogeneous networks; homogeneous and heterogeneous networks; locality-aware; Meta-learning; Metalearning; Representation learning; Tail; tail node embeddings; Task analysis; Artificial Intelligence and Robotics; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8254; https://ink.library.smu.edu.sg/context/sis_research/article/9257/viewcontent/Locality_Aware_Tail_Node_av.pdf
• Institution: Singapore Management University

While the state-of-the-art network embedding approaches often learn high-quality embeddings for high-degree nodes with abundant structural connectivity, the quality of the embeddings for low-degree or nodes is often suboptimal due to their limited structural connectivity. While many real-world networks are long-tailed, to date little effort has been devoted to tail node embeddings. In this article, we formulate the goal of learning tail node embeddings as a problem, given the few links on each tail node. In particular, since each node resides in its own local context, we personalize the regression model for each tail node. To reduce overfitting in the personalization, we propose a meta-learning framework, called , which learns to learn the regression model for the tail nodes at different localities. Moreover, to address the heterogeneity in nodes and edges on heterogeneous information networks (HINs), we further extend the proposed model and formulate , which is based on a dual-adaptation mechanism to facilitate the locality-aware tail node embeddings on HINs. Finally, we conduct extensive experiments and demonstrate the promising results of both meta-tail2vec and its extension meta-tail2vec+.