Paper Detail

PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification

Usman Akram, Matthew Graham, Haris Vikalo

arxiv Score 29.9

Published 2026-11-04 · First seen 2026-11-07

Research Track A · General AI

Abstract

Automatic modulation classification (AMC) is a key component of cognitive wireless systems, enabling spectrum awareness and adaptive communication. Most deep learning approaches to AMC assume a fixed set of modulation classes and access to previously observed training data. In practice, modulation classes and channel conditions may evolve over time, while storage or data-retention constraints may preclude replay of raw baseband I/Q samples. We propose PRISM-AMC, a replay-free continual learning framework that mitigates catastrophic forgetting by preserving task-relevant subspaces of intermediate representations via gradient projection memory. We further analyze projected stochastic-gradient updates under an SNR-dependent gradient-noise model. PRISM-AMC is evaluated in both class-incremental and domain-incremental settings. Experiments on the MIGOU and DeepSig 2018.01A datasets show substantially reduced forgetting relative to sequential fine-tuning and elastic weight consolidation, while remaining competitive with or outperforming replay-based RSD-AMC in class-incremental settings, without storing raw I/Q samples.

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{akram2026prism,
  title = {PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification},
  author = {Usman Akram and Matthew Graham and Haris Vikalo},
  year = {2026},
  abstract = {Automatic modulation classification (AMC) is a key component of cognitive wireless systems, enabling spectrum awareness and adaptive communication. Most deep learning approaches to AMC assume a fixed set of modulation classes and access to previously observed training data. In practice, modulation classes and channel conditions may evolve over time, while storage or data-retention constraints may preclude replay of raw baseband I/Q samples. We propose PRISM-AMC, a replay-free continual learning },
  url = {https://arxiv.org/abs/2611.06066},
  keywords = {cs.LG, eess.SP},
  eprint = {2611.06066},
  archiveprefix = {arXiv},
}

Metadata

{}