PET-TURTLE: Deep Unsupervised Support Vector Machines for Imbalanced Data Clusters

2026-01-06

IEEE Signal Processing Letters

AI Summary

This work addresses the challenge of suboptimal separating hyperplanes and high clustering errors in deep unsupervised clustering when applied to class-imbalanced data. To mitigate these issues, we propose an enhanced TURTLE algorithm that integrates a power-law prior into the deep unsupervised SVM framework—a novel incorporation that, combined with sparse logits for label assignment, effectively alleviates the over-prediction of minority classes. Experimental results demonstrate that the proposed method significantly improves clustering accuracy on both synthetic and real-world imbalanced datasets. Moreover, it consistently outperforms existing approaches across both balanced and imbalanced scenarios, exhibiting strong robustness and generalization capability.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Foundation vision, audio, and language models enable zero-shot performance on downstream tasks via their latent representations. Recently, unsupervised learning of data group structure with deep learning methods has gained popularity. TURTLE, a state of the art deep clustering algorithm, uncovers data labeling without supervision by alternating label and hyperplane updates, maximizing the hyperplane margin, in a similar fashion to support vector machines (SVMs). However, TURTLE assumes clusters are balanced; when data is imbalanced, it yields non-ideal hyperplanes that cause higher clustering error. We propose PET-TURTLE, which generalizes the cost function to handle imbalanced data distributions by a power law prior. Additionally, by introducing sparse logits in the labeling process, PET-TURTLE optimizes a simpler search space that in turn improves accuracy for balanced datasets. Experiments on synthetic and real data show that PET-TURTLE improves accuracy for imbalanced sources, prevents over-prediction of minority clusters, and enhances overall clustering.

Problem

• imbalanced data
• deep clustering
• unsupervised learning
• support vector machines
• cluster imbalance

Innovation

• imbalanced data clustering
• deep unsupervised learning
• power law prior
• sparse logits
• support vector machines