Back to feed
arXiv cs.LG
arXiv cs.LG
7/16/2026
Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges

Federated Explainable Artificial Intelligence: Roles, Architectures, Evaluation, and Open Challenges

Short summary

This survey systematically reviews Federated Explainable AI (FedXAI), the intersection of privacy-preserving federated learning and explainable AI. It introduces a taxonomy classifying methods by the role of explainability, model types, explanation scope, integration level, FL settings, and data heterogeneity. The authors identify key open challenges including explainability under non-IID data, explanation-centric security threats, and the lack of standardized benchmarks for measuring explanation quality and privacy leakage in federated settings.

  • •Comprehensive survey of Federated Explainable AI (FedXAI) with a structured taxonomy
  • •Covers transition of explainability from post-hoc tool to integral FL lifecycle component
  • •Identifies open challenges: non-IID explainability, security threats, missing benchmarks

Generated with AI, which can make mistakes.

#research-breakthrough#regulation-policy
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Comments

Failed to load comments. Please try again.

Explore more

Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
arXiv cs.LG
Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data
arXiv cs.LG
WHERE to Generate Matters: Budget-Aware Synthetic Augmentation for Label Skewed Federated Learning
arXiv cs.LG
Stop Leaking Medical Data! Build a Privacy-First Skin Cancer Classifier with Federated Learning & PySyft 🩺🛡️
Dev.to