Adaptive Self-supervised Robust Clustering for Unstructured Data with Unknown Cluster Number

TL;DR

This paper presents ASRC, a self-supervised deep clustering method that adaptively learns graph structures and does not require prior knowledge of cluster numbers, achieving superior results on benchmark datasets.

Contribution

The paper introduces a novel adaptive self-supervised clustering approach that learns graph structures and cluster prototypes without prior cluster number knowledge.

Findings

Outperforms existing clustering methods on seven benchmark datasets.

Effectively handles unstructured data without pre-specified cluster numbers.

Demonstrates robustness and superior accuracy compared to prior models.

Abstract

We introduce a novel self-supervised deep clustering approach tailored for unstructured data without requiring prior knowledge of the number of clusters, termed Adaptive Self-supervised Robust Clustering (ASRC). In particular, ASRC adaptively learns the graph structure and edge weights to capture both local and global structural information. The obtained graph enables us to learn clustering-friendly feature representations by an enhanced graph auto-encoder with contrastive learning technique. It further leverages the clustering results adaptively obtained by robust continuous clustering (RCC) to generate prototypes for negative sampling, which can further contribute to promoting consistency among positive pairs and enlarging the gap between positive and negative samples. ASRC obtains the final clustering results by applying RCC to the learned feature representations with their consistent graph structure and edge weights. Extensive experiments conducted on seven benchmark datasets demonstrate the efficacy of ASRC, demonstrating its superior performance over other popular clustering models. Notably, ASRC even outperforms methods that rely on prior knowledge of the number of clusters, highlighting its effectiveness in addressing the challenges of clustering unstructured data.