Tech Xplore

New federated learning algorithm enables private, robust, and fast AI development

Three heads are better than one. Versions of this proverb are found worldwide and throughout history. Yet in the race to ...

Study compares machine learning models of raindrop formation

Raindrops form inside clouds when tiny particles of water collide and stick together, forming larger droplets that eventually ...
Psychology Today

Educational Psychology Improves Use of AI for Learning

Students will use AI. The challenge is teaching them to use it in ways that strengthen learning. Educational psychology ...
Frontiers

Asynchronous-first as an ethical imperative: rethinking time, presence, and equity in teacher professional development

Professional development for in-service teachers has long assumed synchronous participation as the pedagogical norm, positioning asynchronous formats as pragmatic concessions to logistical constraint.
IEEE

Adaptive Semi-Asynchronous Federated Learning Over Wireless Networks

Abstract: Owing to the heterogeneous computation and communication capabilities among clients, the synchronous model aggregation in wireless federated learning (FL) is susceptible to the straggler ...
IEEE

Staleness-Controlled Asynchronous Federated Learning: Accuracy and Efficiency Tradeoff

Federated Learning (FL) is an emerging distributed learning paradigm with the privacy-preserving advantage of collaboratively training a shared model across multiple participants. Considering the ...