Rethinking Deep Clustering Paradigms: Self-Supervision Is All You Need

2025-03-05

AI Summary

This paper addresses three fundamental challenges in deep clustering—feature randomness, drift, and distortion—arising from pseudo-supervision. We propose the first purely self-supervised, two-stage paradigm: (1) instance-level contrastive learning to learn discriminative representations, followed by (2) neighborhood-level graph constraints to enforce structural consistency—all without relying on pseudo-labels. Our method integrates a momentum encoder with phased self-supervised optimization to ensure stable and smooth representation learning. Evaluated on six benchmark datasets, it consistently outperforms state-of-the-art methods, achieving an average 3.2% improvement in clustering accuracy. Moreover, it significantly enhances feature consistency and semantic structure preservation. The proposed framework establishes a new, interpretable, and robust paradigm for deep clustering.

Technology Category

• Machine Learning: Clustering
• Computer Vision: Representation Learning for Vision
• Search and Optimization: Learning to Search

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

The recent advances in deep clustering have been made possible by significant progress in self-supervised and pseudo-supervised learning. However, the trade-off between self-supervision and pseudo-supervision can give rise to three primary issues. The joint training causes Feature Randomness and Feature Drift, whereas the independent training causes Feature Randomness and Feature Twist. In essence, using pseudo-labels generates random and unreliable features. The combination of pseudo-supervision and self-supervision drifts the reliable clustering-oriented features. Moreover, moving from self-supervision to pseudo-supervision can twist the curved latent manifolds. This paper addresses the limitations of existing deep clustering paradigms concerning Feature Randomness, Feature Drift, and Feature Twist. We propose a new paradigm with a new strategy that replaces pseudo-supervision with a second round of self-supervision training. The new strategy makes the transition between instance-level self-supervision and neighborhood-level self-supervision smoother and less abrupt. Moreover, it prevents the drifting effect that is caused by the strong competition between instance-level self-supervision and clustering-level pseudo-supervision. Moreover, the absence of the pseudo-supervision prevents the risk of generating random features. With this novel approach, our paper introduces a Rethinking of the Deep Clustering Paradigms, denoted by R-DC. Our model is specifically designed to address three primary challenges encountered in Deep Clustering: Feature Randomness, Feature Drift, and Feature Twist. Experimental results conducted on six datasets have shown that the two-level self-supervision training yields substantial improvements.

Problem

• Addresses Feature Randomness in deep clustering paradigms.
• Mitigates Feature Drift caused by pseudo-supervision.
• Resolves Feature Twist in latent manifolds during training.

Innovation

• Replaces pseudo-supervision with self-supervision training
• Smoother transition between self-supervision levels
• Prevents feature randomness, drift, and twist