You Never Cluster Alone

by   Yuming Shen, et al.

Recent advances in self-supervised learning with instance-level contrastive objectives facilitate unsupervised clustering. However, a standalone datum is not perceiving the context of the holistic cluster, and may undergo sub-optimal assignment. In this paper, we extend the mainstream contrastive learning paradigm to a cluster-level scheme, where all the data subjected to the same cluster contribute to a unified representation that encodes the context of each data group. Contrastive learning with this representation then rewards the assignment of each datum. To implement this vision, we propose twin-contrast clustering (TCC). We define a set of categorical variables as clustering assignment confidence, which links the instance-level learning track with the cluster-level one. On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster. We further propose heuristic cluster augmentation equivalents to enable cluster-level contrastive learning. On the other hand, we derive the evidence lower-bound of the instance-level contrastive objective with the assignments. By reparametrizing the assignment variables, TCC is trained end-to-end, requiring no alternating steps. Extensive experiments show that TCC outperforms the state-of-the-art on challenging benchmarks.


page 1

page 2

page 3

page 4


Few-Example Clustering via Contrastive Learning

We propose Few-Example Clustering (FEC), a novel algorithm that performs...

Graph Contrastive Clustering

Recently, some contrastive learning methods have been proposed to simult...

Contrastive Clustering

In this paper, we propose a one-stage online clustering method called Co...

Adversarial Contrastive Learning by Permuting Cluster Assignments

Contrastive learning has gained popularity as an effective self-supervis...

Large-Scale Hyperspectral Image Clustering Using Contrastive Learning

Clustering of hyperspectral images is a fundamental but challenging task...

Click-through Rate Prediction with Auto-Quantized Contrastive Learning

Click-through rate (CTR) prediction becomes indispensable in ubiquitous ...

LoCo: Local Contrastive Representation Learning

Deep neural nets typically perform end-to-end backpropagation to learn t...