Deep Amortized Relational Model with Group-Wise Hierarchical Generative Process

Authors

  • Huafeng Liu Beijing Jiaotong University The University of Hong Kong
  • Tong Zhou Beijing Jiaotong University
  • Jiaqi Wang Beijing Jiaotong University

DOI:

https://doi.org/10.1609/aaai.v36i7.20720

Keywords:

Machine Learning (ML), Data Mining & Knowledge Management (DMKM)

Abstract

In this paper, we propose Deep amortized Relational Model (DaRM) with group-wise hierarchical generative process for community discovery and link prediction on relational data (e.g., graph, network). It provides an efficient neural relational model architecture by grouping nodes in a group-wise view rather than node-wise or edge-wise view. DaRM simultaneously learns what makes a group, how to divide nodes into groups, and how to adaptively control the number of groups. The dedicated group generative process is able to sufficiently exploit pair-wise or higher-order interactions between data points in both inter-group and intra-group, which is useful to sufficiently mine the hidden structure among data. A series of experiments have been conducted on both synthetic and real-world datasets. The experimental results demonstrated that DaRM can obtain high performance on both community detection and link prediction tasks.

Downloads

Published

2022-06-28

How to Cite

Liu, H., Zhou, T., & Wang, J. (2022). Deep Amortized Relational Model with Group-Wise Hierarchical Generative Process. Proceedings of the AAAI Conference on Artificial Intelligence, 36(7), 7550-7557. https://doi.org/10.1609/aaai.v36i7.20720

Issue

Section

AAAI Technical Track on Machine Learning II