arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.18396cs.LGeess.SPmath.PRstat.APstat.ML
收藏

通过部分模型共享实现通信高效的拜占庭鲁棒联邦共形预测

Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharing

Department of Electronic Systems, Norwegian University of Science and Technology(电子系统系,挪威科学技术大学);Commonwealth Scientific and Industrial Research Organisation(澳大利亚联邦科学与工业研究组织);Department of Information and Communications Engineering, Aalto University(信息与通信工程系,艾尔托大学)

Ehsan Lari, Reza Arablouei, Stefan Werner

AI总结:

PRISM-FCP框架用于联邦共形预测,训练时通过部分模型共享减轻中毒攻击,校准阶段用直方图过滤对抗校准提交,端到端减轻攻击,实验表明其在拜占庭设置中覆盖率高、避免区间膨胀且通信减少,是强大且高效的联邦不确定性量化方法。

摘要:

我们提出了PRISM-FCP(用于联邦共形预测的部分共享和具有统计边际的鲁棒校准),这是一个通信高效的拜占庭鲁棒联邦共形预测框架。它使用部分模型共享来减轻训练期间的随机模型中毒攻击,并使用基于直方图的过滤来减轻对抗性校准提交。现有方法仅在校准阶段解决对抗行为,而PRISM-FCP端到端减轻攻击。训练时客户端通过每轮仅传输D个参数中的M个来部分共享更新,在校准阶段,客户端将不一致分数转换为特征向量,计算基于距离的恶意分数,并在估计共形分位数之前降低或过滤可疑的拜占庭贡献。在合成数据和UCI超导数据集上的大量实验表明,PRISM-FCP在研究的拜占庭设置中保持接近标称的经验覆盖率,同时避免了标准FCP中观察到的区间膨胀,且通信减少。这些结果支持PRISM-FCP作为一种强大且通信高效的联邦不确定性量化方法。

英文摘要:

We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a communication-efficient Byzantine-robust federated conformal prediction framework that uses partial model sharing to mitigate stochastic model-poisoning attacks during training and histogram-based filtering to mitigate adversarial calibration submissions. Existing robust FCP approaches primarily address adversarial behavior during calibration, leaving training-stage poisoning to separate robust-training mechanisms. PRISM-FCP instead considers the coupling between the two stages. During training, clients partially share updates by transmitting only $M$ of $D$ parameters per round. Under the stated stochastic attack model, this attenuates the expected energy of each Byzantine client's perturbation contribution to the aggregate by a factor of $M/D$ relative to full sharing. When this benefit outweighs the optimization slowdown caused by partial updates, it can reduce training error and improve interval efficiency. During calibration, the server uses client-provided characterization vectors to filter suspected Byzantine clients before estimating the conformal quantile from the retained clients. Experiments on synthetic benchmarks and the UCI Superconductivity and YearPredictionMSD datasets, including Gaussian, ALIE, and sign-flipping training-stage attacks, demonstrate near-nominal empirical coverage and favorable communication--performance tradeoffs in the studied settings.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑