Clustering of Incomplete Data via a Bipartite Graph Structure

2025-05-13

AI Summary

This paper addresses the challenging problem of clustering incomplete bipartite graphs with heavy-tailed data distributions and missing central nodes—common in financial applications. Methodologically, it proposes a robust clustering framework that operates without observing central nodes, built upon a generative model grounded in bipartite graph structure, employing non-Gaussian likelihoods (e.g., Student’s *t*-distribution) to accommodate heavy tails, and integrating an end-to-end joint optimization inference scheme. The key contribution is the first bipartite graph clustering method that completely eliminates reliance on central-node observations while significantly enhancing robustness to both high missingness rates and heavy-tailed noise. Empirical evaluation on real-world financial data demonstrates a 12.7% improvement in clustering accuracy over spectral clustering and Gaussian graph models; notably, performance remains stable even under 40% central-node missingness.

Technology Category

• Machine Learning: Clustering
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics

Abstract

There are various approaches to graph learning for data clustering, incorporating different spectral and structural constraints through diverse graph structures. Some methods rely on bipartite graph models, where nodes are divided into two classes: centers and members. These models typically require access to data for the center nodes in addition to observations from the member nodes. However, such additional data may not always be available in many practical scenarios. Moreover, popular Gaussian models for graph learning have demonstrated limited effectiveness in modeling data with heavy-tailed distributions, which are common in financial markets. In this paper, we propose a clustering method based on a bipartite graph model that addresses these challenges. First, it can infer clusters from incomplete data without requiring information about the center nodes. Second, it is designed to effectively handle heavy-tailed data. Numerical experiments using real financial data validate the efficiency of the proposed method for data clustering.

Problem

• Clustering incomplete data without center node information
• Handling heavy-tailed data distributions effectively
• Improving bipartite graph models for financial data

Innovation

• Bipartite graph clustering without center node data
• Handles heavy-tailed distributions effectively
• Incomplete data clustering via bipartite structure