跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.17944 · v1

Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification

首次提交 2026-11-13 17:31
版本更新 2026-11-13 17:31
雷达观测 2026-11-16 11:42
arXiv ↗PDF ↗

摘要

Federated learning (FL) under differential privacy (DP) is typically evaluated on large client cohorts, where subsampling and cross-client averaging amplify privacy and smooth injected noise. Personal biosignal applications such as wearable EEG instead involve small federations of a handful of subjects, a regime whose interaction with formal client-level DP is largely uncharacterized. We study differentially private federated class-incremental learning in this small-cohort regime, combining a public EEG dataset with a custom four-channel MUSE 2 recording set into a K=5-client federation, and give a masked per-class training protocol that avoids degenerate gradients and missing negative supervision under class-incremental streaming. We propose FedEEG, combining Synaptic-Intelligence consolidation with a lagged adaptive FedProx term, and show it reduces catastrophic forgetting relative to FedAvg, FedProx, and a federated Learning-without-Forgetting baseline; on-device balanced-batch replay reduces mean forgetting by a further 56.7%. A class-scoping diagnosis yields 50.5%±3.6%50.5\%\pm3.6\% accuracy with 6 seeds and 2.02 times chance. We also introduce head-scoped client-level DP, which protects the classification head and alone reduces the achievable ε\varepsilon by 200 times at a matched round budget; combined with fewer communication rounds it reaches ε ⁣≈ ⁣10.4\varepsilon\!\approx\!10.4 with utility not statistically distinguishable from non-private training.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-13 17:31 · 最新观测版本

Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification

Federated learning (FL) under differential privacy (DP) is typically evaluated on large client cohorts, where subsampling and cross-client averaging amplify privacy and smooth injected noise. Personal biosignal applications such as wearable EEG instead involve small federations of a handful of subjects, a regime whose interaction with formal client-level DP is largely uncharacterized. We study differentially private federated class-incremental learning in this small-cohort regime, combining a public EEG dataset with a custom four-channel MUSE 2 recording set into a K=5-client federation, and give a masked per-class training protocol that avoids degenerate gradients and missing negative supervision under class-incremental streaming. We propose FedEEG, combining Synaptic-Intelligence consolidation with a lagged adaptive FedProx term, and show it reduces catastrophic forgetting relative to FedAvg, FedProx, and a federated Learning-without-Forgetting baseline; on-device balanced-batch replay reduces mean forgetting by a further 56.7%. A class-scoping diagnosis yields 50.5%±3.6%50.5\%\pm3.6\% accuracy with 6 seeds and 2.02 times chance. We also introduce head-scoped client-level DP, which protects the classification head and alone reduces the achievable ε\varepsilon by 200 times at a matched round budget; combined with fewer communication rounds it reaches ε ⁣≈ ⁣10.4\varepsilon\!\approx\!10.4 with utility not statistically distinguishable from non-private training.

查看此版本解读 →查看此版本原文 ↗