Federated Explainable AI Surveyed: Privacy Meets Transparency

This paper surveys the emerging field of Federated Explainable Artificial Intelligence (FedXAI), which combines federated learning's privacy-preserving approach with explainable AI's focus on transparency. The authors propose a taxonomy to classify existing FedXAI methods based on factors like the role of explainability, model types, and integration levels. They also highlight challenges such as explainability with non-IID data, security threats related to explanations, and the need for standardized evaluation metrics. AI

IMPACT This survey consolidates research on combining privacy-preserving federated learning with AI transparency, identifying key challenges and future directions for trustworthy AI systems.

RANK_REASON The item is a survey paper on a specific AI research area. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• explainable AI
• Federated Explainable Artificial Intelligence
• federated learning
• FedXAI

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →