利用训练中自然产生的信号实现高效联邦聚合，无需修改模型结构。
Intrinsic Training Signals for Federated Learning Aggregation
- 基于特征统计方差加权聚合分类器，利用训练时自生信号。
- 通过SHAP分析参数更新模式，驱动可解释的LoRA合并方法。
- 无需额外架构改动，兼容现有联邦学习框架，性能领先。
联邦学习（FL）可在保护数据隐私的前提下实现分布式客户端协同建模。现有聚合客户端分类头和骨干网络参数的方法通常需修改网络结构或损失函数，而本文提出LIVAR（基于层重要性与方差的融合），创新性地利用标准优化过程中已存在的内在训练信号：一是利用自然涌现的特征统计量进行方差加权的分类器聚合；二是基于对已有参数更新模式的SHAP分析，设计可解释的LoRA融合策略。该方法无需任何架构开销，在多个基准测试上达到当前最优性能，且可无缝集成至现有联邦学习流程。本工作表明，仅依赖现有训练信号即可实现高效模型聚合，为联邦学习聚合提供了新范式。代码已公开于https://github.com/aimagelab/fed-mammoth。
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy. While existing approaches for aggregating client-specific classification heads and adapted backbone parameters require architectural modifications or loss function changes, our method uniquely leverages intrinsic training signals already available during standard optimization. We present LIVAR (Layer Importance and VARiance-based merging), which introduces: i) a variance-weighted classifier aggregation scheme using naturally emergent feature statistics, and ii) an explainability-driven LoRA merging technique based on SHAP analysis of existing update parameter patterns. Without any architectural overhead, LIVAR achieves state-of-the-art performance on multiple benchmarks while maintaining seamless integration with existing FL methods. This work demonstrates that effective model merging can be achieved solely through existing training signals, establishing a new paradigm for efficient federated model aggregation. The code is available at https://github.com/aimagelab/fed-mammoth.
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。