Entity · paper

Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation

paperactiveunsupervised-continual-clustering-via-forward-backward-knowledge-distillation-456db579·1 events·first seen Jun 8, 2026

Aliases: Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation, Forward-Backward Knowledge Distillation for Continual Clustering

More like this (12)

knowledge distillation Sparse Subspace-to-Expert Sharing for Task-Agnostic Continual Learning Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation Weak-to-Strong Generalization via Direct On-Policy Distillation Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation on-policy distillation In-context Vector Distillation FlashbackCL: Mitigating Temporal Forgetting in Federated Learning Visual Attribution Distillation Learning from the Self-future: On-policy Self-distillation for dLLMs FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation

Recent events (1)

4arXiv · cs.LG·Jun 8, 2026·source ↗

FBCC: Forward-Backward Knowledge Distillation for Unsupervised Continual Clustering

A new arXiv preprint introduces Unsupervised Continual Clustering (UCC) as a problem formulation and proposes FBCC, a method using a continual teacher network with task-specific student networks to learn sequential clustering tasks without labels or stored past data. The approach uses a dual-phase forward-backward distillation process to preserve previously discovered cluster structure while learning new ones. Experiments on four benchmark datasets show FBCC outperforms continual learning baselines in clustering accuracy while reducing catastrophic forgetting.

Evaluation and Benchmarking Unsupervised Continual Clustering via Forward-Backward Knowledge Distillation