Practical Recommendations for Replay-based Continual Learning Methods
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 Learning challenge. Among them, Replay approaches have empirically proved to be the most effective ones. Replay operates by saving some samples in memory which are then used to rehearse knowledge during training in subsequent tasks. However, an extensive comparison and deeper understanding of different replay implementation subtleties is still missing in the literature. The aim of this work is to compare and analyze existing replay-based strategies and provide practical recommendations on developing efficient, effective and generally applicable replay-based strategies. In particular, we investigate the role of the memory size value, different weighting policies and discuss about the impact of data augmentation, which allows reaching better performance with lower memory sizes.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningData AugmentationSimilar Papers 제목 키워드 기반
The Effectiveness of World Models for Continual Reinforcement Learning
World models power some of the most efficient reinforcement learning algorithms. In this work, we showcase that they can be harnessed for continual learning - a situation when the agent faces changing environments. World…
Continual LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1A Benchmark and Empirical Analysis for Replay Strategies in Continual Learning
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…
Continual LearningCoordinated Replay Sample Selection for Continual Federated Learning
Continual Federated Learning (CFL) combines Federated Learning (FL), the decentralized learning of a central model on a number of client devices that may not communicate their data, and Continual Learning (CL), the learn…
Continual LearningFederated LearningStable Continual Reinforcement Learning via Diffusion-based Trajectory Replay
Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making ta…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers
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