4 papers
Decoupling Inference from State Updates in Low-Latency Feature Engines via Probabilistic Thinning
Augusto Peres, Iker Perez, Pedro Valdeira +4
Streaming data systems increasingly underpin Machine Learning workflows that maintain large numbers of continuously updated aggregations. In production settings, each incoming even…
A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning
Pedro Valdeira, Yuejie Chi, Cláudia Soares +1
Most federated learning (FL) methods use a client-server scheme, where clients communicate only with a central server. However, this scheme is prone to bandwidth bottlenecks at the…
Vertical Federated Learning with Missing Features During Training and Inference
Pedro Valdeira, Shiqiang Wang, Yuejie Chi
Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume th…
Communication-efficient Vertical Federated Learning via Compressed Error Feedback
Pedro Valdeira, João Xavier, Cláudia Soares +1
Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and…