Paper Detail

Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge

Wonseon Lim, Jaesung Lee, Dae-Won Kim

arxiv Score 11.5

Published 2026-04-08 · First seen 2026-04-10

Research Track A · General AI

Abstract

Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly on accuracy or inference-time performance, often overlooking the memory and computational costs of on-device training. In this paper, we propose CPS-Prompt, a critical patch-aware sparse prompting framework that explicitly targets training-time memory usage and computational cost by integrating critical patch sampling (CPS) for task-aware token reduction and decoupled prompt and classifier training (DPCT) to reduce backpropagation overhead. Experiments on three public benchmarks and real edge hardware show that CPS-Prompt improves peak memory, training time, and energy efficiency by about 1.6x over the balanced CODA-Prompt baseline, while maintaining accuracy within 2% of the state-of-the-art C-Prompt on average and remaining competitive with CODA-Prompt in accuracy. The code is available at https://github.com/laymond1/cps-prompt.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{lim2026critical,
  title = {Critical Patch-Aware Sparse Prompting with Decoupled Training for Continual Learning on the Edge},
  author = {Wonseon Lim and Jaesung Lee and Dae-Won Kim},
  year = {2026},
  abstract = {Continual learning (CL) on edge devices requires not only high accuracy but also training-time efficiency to support on-device adaptation under strict memory and computational constraints. While prompt-based continual learning (PCL) is parameter-efficient and achieves competitive accuracy, prior work has focused mainly on accuracy or inference-time performance, often overlooking the memory and computational costs of on-device training. In this paper, we propose CPS-Prompt, a critical patch-aware},
  url = {https://arxiv.org/abs/2604.07399},
  keywords = {cs.LG},
  eprint = {2604.07399},
  archiveprefix = {arXiv},
}

Metadata

{}