Federated learning, differential privacy, and privacy-preserving machine learning. We cover how models train across devices and institutions without centralizing data, what privacy guarantees actually cost in accuracy, and the benchmarks and frameworks shaping the field, always traced back to the original research.
ProtoSig replaces thousands of random forgeries with 50 clustered prototype signatures, cutting training compute by over 98% while matching verification accuracy — and making signature verification fairer and more stable.
A criterion-wise local differential privacy framework perturbs each rating dimension on-device before it reaches the server — here’s what that privacy costs in recommendation accuracy.
What Happens When You Add Differential Privacy to a Multi-Criteria Recommender System Read More »
Federated recommenders drift apart when clients simply average parameters. AlignFedRec shares item similarity matrices instead, aligning structure rather than embeddings.
Why Federated Recommenders Break and How Structural Alignment Fixes Them Read More »
PFLlib benchmarks traditional and personalized federated learning algorithms across three heterogeneity scenarios, giving the field a common yardstick.
PFLlib Brings Order to Personalized Federated Learning Research Read More »
Mean Aggregator Beats Robust Aggregators Under Label Poisoning Attacks on Heterogeneous Data | AI Trend Blend AITrendBlend Machine Learning Cybersecurity About Federated Learning Security · Journal of Machine Learning Research 26 (2025) 1–51 · 18 min read The Aggregator Everyone Dismissed Just Turned Out to Be the Best Defense Against Label Poisoning A team from
The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond | Research Breakdown AITrendBlend Machine Learning Agent AI About Federated RL · Journal of Machine Learning Research 26 (2025) 1–85 · 22 min read When Different Agents Learn Different Things: Why Heterogeneity Is Actually a Gift in Federated Q-Learning A team from Carnegie Mellon
The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond Read More »
Dist-SI: Selective Inference with Distributed Data via Randomized Lasso | AI Trend Blend AITrendBlend Machine Learning Computer Vision About Statistical Inference · Journal of Machine Learning Research 26 (2025) 1–44 · 20 min read How Dist-SI Lets Hospitals Run Joint Studies Without Sharing Patient Records — Selective Inference Across Distributed Data Sifan Liu (Stanford) and
Dist-SI: Selective Inference with Distributed Data via Randomized Lasso Read More »
Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback | AI Trend Blend AITrendBlend Machine Learning Computer Vision About Federated Learning · Journal of Machine Learning Research 26 (2025) 1–67 · 18 min read The Sampling Problem Federated Learning Has Been Ignoring — and How OSMD Finally Fixes It A multi-institution team
Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback Read More »
DisC2o-HD: Distributed Causal Inference with Covariate Shift for High-Dimensional Healthcare Data | AI Trend Blend AITrendBlend Healthcare AI Math Applications About Healthcare AI · Journal of Machine Learning Research 26 (2025) · Penn / Columbia / Cornell · 20 min read DisC2o-HD: How Researchers Are Solving the Privacy-Accuracy Trade-off in Multi-Hospital Causal Inference A team
FedLSC: Federated Learning with Layer Similarity Comparison for Skin Cancer | AI Trend Blend AITrendBlend Machine Learning Computer Vision Medical AI About Federated Learning · Expert Systems With Applications 306 (2026) 130937 · 22 min read FedLSC: The Smarter Way to Train a Skin Cancer AI Across Hospitals Without Sharing Any Patient Data Researchers at
FedLSC: Federated Learning with Layer Similarity Comparison for Skin Cancer Read More »