融合联邦学习与可解释AI，探索隐私保护下的模型透明化路径
Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review
- 分析联邦学习与可解释AI的协同机制，揭示两者交互关系
- 37项研究中仅1项量化评估联邦学习对解释性的影响，存在明显空白
- 适合关注隐私计算与模型可解释性的研究人员参考
联邦学习（FL）与可解释人工智能（XAI）的联合应用可在保护隐私的前提下实现分布式数据建模并解释模型内部机制。为厘清二者协同带来的优势与矛盾，本综述系统梳理了同时涉及FL与模型可解释性或事后解释的研究。在符合标准的37项研究中，仅有1项明确且定量分析了联邦学习对模型解释的影响，显示研究仍存在显著空白。联邦节点的解释性指标聚合导致全局洞察虽增强，但局部模式信息被稀释。部分研究提出融合解释方法的联邦算法，以防范默认或恶意节点的风险。然而，采用成熟联邦学习库或遵循报告规范的研究仍属少数。亟需更多量化研究与结构化、透明化的实践，以深入理解二者相互作用的条件与机制。
原文摘要 · Abstract (English)
The joint implementation of federated learning (FL) and explainable artificial intelligence (XAI) could allow training models from distributed data and explaining their inner workings while preserving essential aspects of privacy. Toward establishing the benefits and tensions associated with their interplay, this scoping review maps the publications that jointly deal with FL and XAI, focusing on publications that reported an interplay between FL and model interpretability or post-hoc explanations. Out of the 37 studies meeting our criteria, only one explicitly and quantitatively analyzed the influence of FL on model explanations, revealing a significant research gap. The aggregation of interpretability metrics across FL nodes created generalized global insights at the expense of node-specific patterns being diluted. Several studies proposed FL algorithms incorporating explanation methods to safeguard the learning process against defaulting or malicious nodes. Studies using established FL libraries or following reporting guidelines are a minority. More quantitative research and structured, transparent practices are needed to fully understand their mutual impact and under which conditions it happens.
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。