Multi-way Clustering and Discordance Analysis through Deep Collective Matrix Tri-Factorization

TL;DR

This paper introduces a neural collective matrix tri-factorization method for multi-way clustering and discordance analysis, enabling spectral clustering of heterogeneous data and revealing discrepancies across matrices for improved knowledge base quality and representation learning.

Contribution

It presents the first neural approach for collective matrix tri-factorization and introduces Discordance Analysis for discrepancy detection in multi-matrix data collections.

Findings

Outperforms previous non-neural methods on benchmark datasets

Effectively reveals discrepancies across matrices in knowledge bases

Enhances representation learning through multi-way clustering

Abstract

Heterogeneous multi-typed, multimodal relational data is increasingly available in many domains and their exploratory analysis poses several challenges. We advance the state-of-the-art in neural unsupervised learning to analyze such data. We design the first neural method for collective matrix tri-factorization of arbitrary collections of matrices to perform spectral clustering of all constituent entities and learn cluster associations. Experiments on benchmark datasets demonstrate its efficacy over previous non-neural approaches. Leveraging signals from multi-way clustering and collective matrix completion we design a unique technique, called Discordance Analysis, to reveal information discrepancies across subsets of matrices in a collection with respect to two entities. We illustrate its utility in quality assessment of knowledge bases and in improving representation learning.