用损失值替代模型权重共享，降低隐私风险和传输开销。
Federated Learning Framework via Distributed Mutual Learning
- 客户端定期分享对公共测试集的损失预测，而非模型参数。
- 通过融合本地损失与跨客户端损失的KL散度优化模型。
- 在口罩检测任务中精度更高，且更安全、泛化能力更强。
联邦学习通常依赖于共享完整或部分模型权重，这会增加网络带宽负担并引发隐私风险。本文提出一种基于损失的替代方案，采用分布式互学习机制。客户端不传输模型参数，而是定期共享其在公开测试集上的损失预测结果。每个客户端通过结合自身本地损失与其它客户端损失的平均Kullback-Leibler散度来更新模型。该协作方式有效降低通信开销并增强数据隐私保护。在人脸口罩检测任务上的实验表明，该方法优于传统权重共享基线，在未见数据上达到更高准确率，具备更强泛化能力和隐私优势。
原文摘要 · Abstract (English)
Federated Learning often relies on sharing full or partial model weights, which can burden network bandwidth and raise privacy risks. We present a loss-based alternative using distributed mutual learning. Instead of transmitting weights, clients periodically share their loss predictions on a public test set. Each client then refines its model by combining its local loss with the average Kullback-Leibler divergence over losses from other clients. This collaborative approach both reduces transmission overhead and preserves data privacy. Experiments on a face mask detection task demonstrate that our method outperforms weight-sharing baselines, achieving higher accuracy on unseen data while providing stronger generalization and privacy benefits.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。