提出频域可解释方法FreqX，实现快速高精度模型归因。
Comprehensive and Reliable Feature Attribution for Diverse Modalities and Models via Frequency-Domain Insights
- 基于信号处理与信息论构建频域可解释框架
- 解释速度比基线快至少10倍且含概念信息
- 适合联邦学习中异构设备的高效公平归因
个性化联邦学习（PFL）使客户端在不共享私有数据的前提下协同训练个性化模型。然而，PFL面临非独立同分布（Non-IID）、设备异构、公平性缺失及贡献不清等问题，亟需深度学习模型的可解释性来应对。这些挑战对可解释性提出了低成本、隐私保护和细粒度信息的新要求，而现有方法尚无法满足。本文提出一种新型可解释方法FreqX，引入信号处理与信息论思想。实验表明，FreqX的解释结果同时包含归因信息与概念信息；其运行速度至少比含概念信息的基线快10倍。
原文摘要 · Abstract (English)
Personalized Federal learning(PFL) allows clients to cooperatively train a personalized model without disclosing their private dataset. However, PFL suffers from Non-IID, heterogeneous devices, lack of fairness, and unclear contribution which urgently need the interpretability of deep learning model to overcome these challenges. These challenges proposed new demands for interpretability. Low cost, privacy, and detailed information. There is no current interpretability method satisfying them. In this paper, we propose a novel interpretability method \emph{FreqX} by introducing Signal Processing and Information Theory. Our experiments show that the explanation results of FreqX contain both attribution information and concept information. FreqX runs at least 10 times faster than the baselines which contain concept information.
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。