Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
The majority of online continual learning (CL) advocates single-epoch training and imposes restrictions on the size of replay memory. However, single-epoch training would incur a different amount of computations per CL algorithm, and the additional storage cost to store logit or model in addition to replay memory is largely ignored in calculating the storage budget. Arguing different computational and storage budgets hinder fair comparison among CL algorithms in practice, we propose to use floating point operations (FLOPs) and total memory size in Byte as a metric for computational and memory budgets, respectively, to compare and develop CL algorithms in the same 'total resource budget.' To improve a CL method in a limited total budget, we propose adaptive layer freezing that does not update the layers for less informative batches to reduce computational costs with a negligible loss of accuracy. In addition, we propose a memory retrieval method that allows the model to learn the same amount of knowledge as using random retrieval in fewer iterations. Empirical validations on the CIFAR-10/100, CLEAR-10/100, and ImageNet-1K datasets demonstrate that the proposed approach outperforms the state-of-the-art methods within the same total budget
Code (0)
등록된 구현이 없습니다.
Tasks
Continual LearningRetrievalSimilar Papers 제목 키워드 기반
Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation
Training data for olfaction is scattered through disparate, non-standardized datasets that limit the ability to build representative world models. Olfactory navigation is a highly dynamic and non-stationary task that ben…
Reinforcement LearningImage ClassificationContinual LearningOnline Budgeted Learning for Classifier Induction
In real-world machine learning applications, there is a cost associated with sampling of different features. Budgeted learning can be used to select which feature-values to acquire from each instance in a dataset, such t…
Efficient Self-supervised Continual Learning with Progressive Task-correlated Layer Freezing
Inspired by the success of Self-supervised learning (SSL) in learning visual representations from unlabeled data, a few recent works have studied SSL in the context of continual learning (CL), where multiple tasks are le…
Continual LearningGPUSelf-Supervised LearningAdaptive Budgeted Multi-Armed Bandits for IoT with Dynamic Resource Constraints
Internet of Things (IoT) systems increasingly operate in environments where devices must respond in real time while managing fluctuating resource constraints, including energy and bandwidth. Yet, current approaches often…
Multi-Armed BanditsEXPANSE: A Deep Continual / Progressive Learning System for Deep Transfer Learning
Deep transfer learning techniques try to tackle the limitations of deep learning, the dependency on extensive training data and the training costs, by reusing obtained knowledge. However, the current DTL techniques suffe…
Continual LearningTransfer Learning