Pith. sign in

REVIEW 2 cited by

SIESTA: Efficient Online Continual Learning with Sleep

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.10725 v3 pith:Z6W366KR submitted 2023-03-19 cs.CV cs.LG

classification cs.CVcs.LG
keywords learningcontinualsiestadataefficiencyefficientmemorysleep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In supervised continual learning, a deep neural network (DNN) is updated with an ever-growing data stream. Unlike the offline setting where data is shuffled, we cannot make any distributional assumptions about the data stream. Ideally, only one pass through the dataset is needed for computational efficiency. However, existing methods are inadequate and make many assumptions that cannot be made for real-world applications, while simultaneously failing to improve computational efficiency. In this paper, we propose a novel continual learning method, SIESTA based on wake/sleep framework for training, which is well aligned to the needs of on-device learning. The major goal of SIESTA is to advance compute efficient continual learning so that DNNs can be updated efficiently using far less time and energy. The principal innovations of SIESTA are: 1) rapid online updates using a rehearsal-free, backpropagation-free, and data-driven network update rule during its wake phase, and 2) expedited memory consolidation using a compute-restricted rehearsal policy during its sleep phase. For memory efficiency, SIESTA adapts latent rehearsal using memory indexing from REMIND. Compared to REMIND and prior arts, SIESTA is far more computationally efficient, enabling continual learning on ImageNet-1K in under 2 hours on a single GPU; moreover, in the augmentation-free setting it matches the performance of the offline learner, a milestone critical to driving adoption of continual learning in real-world applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Distribution-aware Online Continual Learning for Urban Spatio-Temporal Forecasting

    cs.LG 2024-11 conditional novelty 6.0 of 10

    DOST adapts urban spatio-temporal forecasting models to drifting data streams using per-location adapters and a periodic awake-hibernate update strategy, cutting forecast error by about 12.9% on four datasets.

  2. Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks

    cs.LG 2025-01 conditional novelty 5.0 of 10

    A systematic review that compiles and categorizes 81 OCL approaches, 83 datasets, and hundreds of associated components and features.

Pith tools