paper-with-me

Papers

Holistic Continual Learning under Concept Drift with Adaptive Memory Realignment

2025-07-03 · Alif Ashrafee, Jedrzej Kozal, Michal Wozniak, Bartosz Krawczyk arxiv

Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of previously learned tasks remains static. This overlooks the dynamic nature of real-world data streams, where concept drift permanently alters previously seen data and demands both stability and rapid adaptation. We introduce a holistic framework for continual learning under concept drift that simulates realistic scenarios by evolving task distributions. As a baseline, we consider Full Relearning (FR), in which the model is retrained from scratch on newly labeled samples from the drifted distribution. While effective, this approach incurs substantial annotation and computational overhead. To address these limitations, we propose Adaptive Memory Realignment (AMR), a lightweight alternative that equips rehearsal-based learners with a drift-aware adaptation mechanism. AMR selectively removes outdated samples of drifted classes from the replay buffer and repopulates it with a small number of up-to-date instances, effectively realigning memory with the new distribution. This targeted resampling matches the performance of FR while reducing the need for labeled data and computation by orders of magnitude. To enable reproducible evaluation, we introduce four concept drift variants of standard vision benchmarks, where previously seen classes reappear with shifted representations. Comprehensive experiments on these datasets using several rehearsal-based baselines show that AMR consistently counters concept drift, maintaining high accuracy with minimal overhead. These results position AMR as a scalable solution that reconciles stability and plasticity in non-stationary continual learning environments. Full implementation of our framework and benchmark datasets is available at: github.com/AlifAshrafee/CL-Under-Concept-Drift.

📄 PDF Abstract BibTeX arXiv:2507.02310

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Class-Incremental Experience Replay for Continual Learning under Concept Drift

2021-04-24 · Łukasz Korycki, Bartosz Krawczyk

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning…

Continual Learningvalid

Efficient Online Continual Foundation Model Fine-Tuning for Predictive Process Monitoring

2026-08-28 · Sjoerd van Straten, Marwan Hassani arxiv

Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online co…

Continual Learning

Unlocking Compositional Generalization in Continual Few-Shot Learning

2026-05-12 · Phu-Quy Nguyen-Lam, Phu-Hoa Pham, Dao Sy Duy Minh, Chi-Nguyen Tran 외 arxiv

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared acr…

Representation LearningContinual LearningFew-Shot Learning

Optimal Resource Allocation for ML Model Training and Deployment under Concept Drift

2025-12-14 · Hasan Burhan Beytur, Gustavo de Veciana, Haris Vikalo, Kevin S Chan arxiv

We study how to allocate resources for training and deployment of machine learning (ML) models under concept drift and limited budgets. We consider a setting in which a model provider distributes trained models to multip…

Continual Learning

A Hybrid Active-Passive Approach to Imbalanced Nonstationary Data Stream Classification

2022-10-10 · Kleanthis Malialis, Manuel Roveri, Cesare Alippi, Christos G. Panayiotou 외

In real-world applications, the process generating the data might suffer from nonstationary effects (e.g., due to seasonality, faults affecting sensors or actuators, and changes in the users' behaviour). These changes, o…

Drift DetectionIncremental Learning