PME: Projected Metric Embedding on Heterogeneous Networks for Link Prediction

No Thumbnail Available
File version
Author(s)
Chen, Hongxu
Yin, Hongzhi
Wang, Weiqing
Wang, Hao
Quoc, Viet Hung Nguyen
Li, Xue
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)

Rómer Rosales, Jiliang Tang

Date
2018
Size
File type(s)
Location

London, ENGLAND

License
Abstract

Heterogenous information network embedding aims to embed heterogenous information networks (HINs) into low dimensional spaces, in which each vertex is represented as a low-dimensional vector, and both global and local network structures in the original space are preserved. However, most of existing heterogenous information network embedding models adopt the dot product to measure the proximity in the low dimensional space, and thus they can only preserve the first-order proximity and are insufficient to capture the global structure. Compared with homogenous information networks, there are multiple types of links (i.e., multiple relations) in HINs, and the link distribution w.r.t relations is highly skewed. To address the above challenging issues, we propose a novel heterogenous information network embedding model PME based on the metric learning to capture both first-order and second-order proximities in a unified way. To alleviate the potential geometrical inflexibility of existing metric learning approaches, we propose to build object and relation embeddings in separate object space and relation spaces rather than in a common space. Afterwards, we learn embeddings by firstly projecting vertices from object space to corresponding relation space and then calculate the proximity between projected vertices. To overcome the heavy skewness of the link distribution w.r.t relations and avoid "over-sampling'' or "under-sampling'' for each relation, we propose a novel loss-aware adaptive sampling approach for the model optimization. Extensive experiments have been conducted on a large-scale HIN dataset, and the experimental results show superiority of our proposed PME model in terms of prediction accuracy and scalability.

Journal Title
Conference Title

KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING

Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject

Database systems

Persistent link to this record
Citation