Federated Learning

2 summarised stories about Federated Learning, each linking back to the original source. Browse all topics →

Thursday, 16 July 2026

Privacy Preserving Recommender Systems Balancing Personalization with Privacy

arXiv cs.AI 18 hours ago

Researchers developed a privacy-preserving recommendation system framework combining federated learning, differential privacy, and cohort-level modeling for e-commerce platforms. The framework maintained competitive recommendation quality at moderate privacy budgets with epsilon approximately 5, evaluated across metrics including Click-Through Rate, Precision@K, Recall@K, and NDCG@K on synthetic retail datasets. Organizations can now deploy recommendation systems that balance personalization with regulatory compliance requirements without substantially degrading recommendation performance.

AI Compliance & Regulation AI Privacy & Security Federated Learning Recommender Systems

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

arXiv cs.AI 18 hours ago

Researchers surveyed Federated Explainable Artificial Intelligence (FedXAI), which combines federated learning's privacy-preserving training with explainability techniques to improve transparency and trust in distributed machine learning systems. The survey reviews methods across model-agnostic explanations, interpretable models, and explainability-aware aggregation mechanisms, organizing 100+ papers through a taxonomy based on explainability roles and FL settings. Key challenges remain in evaluating explanation quality, securing against explainability-based attacks, and extending XAI to systems with non-identical data distributions across participants.

AI Explainability AI Privacy & Security AI Transparency & Trust Federated Learning