7 papers · 1 filter
Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning
Hongye Xu, Bartosz Krawczyk
Exemplar-free class-incremental learning (EFCIL) requires stable decision boundaries within a shifting feature space. While maintaining class-conditional Gaussian statistics provid…
Sparsity, Superposition, and Forgetting: A Mechanistic Study of Representation Retention in Continual Learning
Jan Wasilewski, Jędrzej Kozal, Michał Woźniak +1
Continual learning (CL) systems often forget previously acquired knowledge, yet the mechanisms driving forgetting remain hard to isolate in practice because real datasets entangle…
Revisiting Prototype Rehearsal for Exemplar-Free Continual Learning: Manifold-Aware Boundary Sampling with Adaptive Class-Balanced Loss
Hongye Xu, Bartosz Krawczyk
Exemplar-free class-incremental learning (EFCIL) aims to acquire new classes over time without storing raw data. Historically, prototype rehearsal, which samples around stored clas…
Two-Way Is Better Than One: Bidirectional Alignment with Cycle Consistency for Exemplar-Free Class-Incremental Learning
Hongye Xu, Bartosz Krawczyk
Continual learning (CL) seeks models that acquire new skills without erasing prior knowledge. In exemplar-free class-incremental learning (EFCIL), this challenge is amplified becau…
Unlearning-based sliding window for continual learning under concept drift
Michal Wozniak, Marek Klonowski, Maciej Maczynski +1
Traditional machine learning assumes a stationary data distribution, yet many real-world applications operate on nonstationary streams in which the underlying concept evolves over…
What is the role of memorization in Continual Learning?
Jędrzej Kozal, Jan Wasilewski, Alif Ashrafee +2
Memorization impacts the performance of deep learning algorithms. Prior works have studied memorization primarily in the context of generalization and privacy. This work studies th…
Balanced Gradient Sample Retrieval for Enhanced Knowledge Retention in Proxy-based Continual Learning
Hongye Xu, Jan Wasilewski, Bartosz Krawczyk
Continual learning in deep neural networks often suffers from catastrophic forgetting, where representations for previous tasks are overwritten during subsequent training. We propo…