REVIEW 3 cited by
Model Zoo: A Growing "Brain" That Learns Continually
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
Signed reviews
read the original abstract
This paper argues that continual learning methods can benefit by splitting the capacity of the learner across multiple models. We use statistical learning theory and experimental analysis to show how multiple tasks can interact with each other in a non-trivial fashion when a single model is trained on them. The generalization error on a particular task can improve when it is trained with synergistic tasks, but can also deteriorate when trained with competing tasks. This theory motivates our method named Model Zoo which, inspired from the boosting literature, grows an ensemble of small models, each of which is trained during one episode of continual learning. We demonstrate that Model Zoo obtains large gains in accuracy on a variety of continual learning benchmark problems. Code is available at https://github.com/grasp-lyrl/modelzoo_continual.
Forward citations
Cited by 3 Pith papers
-
GenFAR: A generalized representation of brain structure, derived from 49,246 multi-cohort MRIs via deep learning
A multi-task deep learning system trained on 49,246 brain MRIs with 17 clinical labels produces transferable brain features that improve downstream prediction accuracy and sample efficiency.
-
SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
SD-LoRA is a rehearsal-free, inference-efficient class-incremental learning method that decouples magnitude and direction in LoRA components and outperforms prior prompt/LoRA methods on several vision benchmarks.
-
IRS: Incremental Relationship-guided Segmentation for Digital Pathology
IRS uses anatomical relationships between old and new classes to guide knowledge distillation in a prompt-driven mixture-of-experts network, improving class-incremental segmentation of kidney pathology compared to baselines.
Discussion (0). Continue with ORCID to comment.