RecTen: A Recursive Hierarchical Low Rank Tensor Factorization Method to Discover Hierarchical Patterns in Multi-modal Data

TL;DR

RecTen is an unsupervised recursive tensor decomposition method that uncovers hierarchical patterns in multi-modal data, enabling the detection of emerging clusters and behaviors in complex datasets like online forums.

Contribution

It introduces a novel recursive hierarchical tensor clustering approach that automatically identifies multi-level structures without ground truth.

Findings

Successfully applied to real-world datasets revealing user behavior patterns.

Able to detect early signals of events like ransomware outbreaks and scams.

Provides a tool for hierarchical structure discovery in multi-modal data.

Abstract

How can we expand the tensor decomposition to reveal a hierarchical structure of the multi-modal data in a self-adaptive way? Current tensor decomposition provides only a single layer of clusters. We argue that with the abundance of multimodal data and time-evolving networks nowadays, the ability to identify emerging hierarchies is important. To this effect, we propose RecTen, a recursive hierarchical soft clustering approach based on tensor decomposition. Our approach enables us to: (a) recursively decompose clusters identified in the previous step, and (b) identify the right conditions for terminating this process. In the absence of proper ground truth, we evaluate our approach with synthetic data and test its sensitivity to different parameters. We also apply RecTen on five real datasets which involve the activities of users in online discussion platforms, such as security forums. This analysis helps us reveal clusters of users with interesting behaviors, including but not limited to early detection of some real events like ransomware outbreaks, the emergence of a blackmarket of decryption tools, and romance scamming. To maximize the usefulness of our approach, we develop a tool which can help the data analysts and overall research community by identifying hierarchical structures. RecTen is an unsupervised approach which can be used to take the pulse of the large multi-modal data and let the data discover its own hidden structures by itself.