# Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation Source: [Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation]() Collection index: [llms.txt]() Data updated: 2026-06-09T05:00:15.114Z Authors: Mohammadreza Sadeghi, Sareh Soleimani, Zihan Wang, Narges Armanfard Published: 2026-06-05T17:28:19.000Z ## Abstract Unsupervised Continual Learning (UCL) aims to enable neural networks to learn sequential tasks without labels or access to past data. A major challenge in this setting is Catastrophic Forgetting, where models forget previously learned tasks upon learning new ones. This challenge is amplified in UCL due to the absence of labels to guide learning and memory retention. Existing mitigation strategies, such as knowledge distillation and replay buffers, often raise memory and privacy concerns. Moreover, current UCL methods largely overlook clustering-specific objectives. To fill this gap, we introduce Unsupervised Continual Clustering (UCC) and propose Forward-Backward Knowledge Distillation for Continual Clustering (FBCC). FBCC employs a continual teacher network with a clustering projector and lightweight task-specific students. Through a dual-phase forward-backward distillation process, the teacher learns new clusters while preserving previously discovered cluster structure without storing past data. FBCC represents a pioneering approach to UCC, demonstrating improved clustering performance across sequential tasks. Experiments on four benchmark datasets demonstrate that FBCC consistently outperforms existing continual learning baselines in clustering accuracy while significantly reducing catastrophic forgetting. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Unsupervised Continual Clustering on Tiny-ImageNet](): Unsupervised Continual Clustering; Tiny-ImageNet; Clustering Accuracy (ACC): 18.36. - [Unsupervised Continual Clustering on CIFAR-100](): Unsupervised Continual Clustering; CIFAR-100; Accuracy: 38.73. - [Unsupervised Continual Clustering on CIFAR-10](): Unsupervised Continual Clustering; CIFAR-10; Accuracy (ACC): 75.28. - [Unsupervised Continual Clustering on ImageNet 100](): Unsupervised Continual Clustering; ImageNet-100; Accuracy (ACC): 43.28. ## Original sources and implementation [Original paper]() [PDF]()