Computationally Budgeted Continual Learning: What Does Matter?
Authors:
- 1 June 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3698-3707
Abstract
Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously seen data, while imposing no constraints on the computational budget for training. This is unreasonable for applications in-the-wild, where systems are primarily constrained by computational and time budgets, not storage. We revisit this problem with a large-scale benchmark and analyze the performance of traditional CL approaches in a compute-constrained setting, where effective memory samples used in training can be implicitly restricted as a consequence of limited computation. We conduct experiments evaluating various CL sampling strategies, distillation losses, and partial fine-tuning on two large-scale datasets, namely ImageNet2K and Continual Google Landmarks V2 in data incremental, class incremental, and time incremental settings. Through extensive experiments amounting to a total of over 1500 GPU-hours, we find that, under compute-constrained setting, traditional CL approaches, with no exception, fail to outperform a simple minimal baseline that samples uniformly from memory. Our conclusions are consistent in a different number of stream time steps, e.g., 20 to 200, and under several computational budgets. This suggests that most existing CL methods are particularly too computationally expensive for realistic budgeted deployment. Code for this project is available at: https://github.com/drimpossible/BudgetCL.Keywords
All Related Versions
Funding Information
- King Abdullah University of Science and Technology (OSR-CRG2021-4648)
- UKRI (EP/W002981/1)
This publication has 26 references indexed in Scilit:
- Learning a Unified Classifier Incrementally via Rebalancing2019
- Large Scale Incremental Learning2019
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning2018
- Growing a Brain: Fine-Tuning by Increasing Model Capacity2017
- Expert Gate: Lifelong Learning with a Network of Experts2017
- iCaRL: Incremental Classifier and Representation Learning2017
- Deep Residual Learning for Image Recognition2016
- Deep learningNature, 2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- ImageNet: A large-scale hierarchical image database2009