paper-with-me

홈 › Papers

A Benchmark and Empirical Analysis for Replay Strategies in Continual Learning

2022-08-04 · Qihan Yang, Fan Feng, Rosa Chan

With the capacity of continual learning, humans can continuously acquire knowledge throughout their lifespan. However, computational systems are not, in general, capable of learning tasks sequentially. This long-standing challenge for deep neural networks (DNNs) is called catastrophic forgetting. Multiple solutions have been proposed to overcome this limitation. This paper makes an in-depth evaluation of the memory replay methods, exploring the efficiency, performance, and scalability of various sampling strategies when selecting replay data. All experiments are conducted on multiple datasets under various domains. Finally, a practical solution for selecting replay methods for various data distributions is provided.

📄 PDF Abstract BibTeX arXiv:2208.02660

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Practical Recommendations for Replay-based Continual Learning Methods

2022-03-19 · Gabriele Merlin, Vincenzo Lomonaco, Andrea Cossu, Antonio Carta 외

Continual Learning requires the model to learn from a stream of dynamic, non-stationary data without forgetting previous knowledge. Several approaches have been developed in the literature to tackle the Continual Learnin…

Continual LearningData Augmentation

Distilled Replay: Overcoming Forgetting through Synthetic Samples

2021-03-29 · Andrea Rosasco, Antonio Carta, Andrea Cossu, Vincenzo Lomonaco 외

Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new data during training. The amount of pat…

Continual Learning

Replay Can Provably Increase Forgetting

2025-06-04 · Yasaman Mahdaviyeh, James Lucas, Mengye Ren, Andreas S. Tolias 외

Continual learning seeks to enable machine learning systems to solve an increasing corpus of tasks sequentially. A critical challenge for continual learning is forgetting, where the performance on previously learned task…

Continual Learning

Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers

2026-04-09 · Danit Yanowsky, Daphna Weinshall arxiv

Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most e…

Continual Learning

Trust Region Continual Learning as an Implicit Meta-Learner

2026-02-02 · Zekun Wang, Anant Gupta, Christopher J. MacLellan arxiv

Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are…

Continual LearningImage Generation