Event-Driven Online Vertical Federated Learning
Preprint
Abstract
Online learning is more adaptable to real-world scenarios in Vertical Federated Learning (VFL) compared to offline learning. However, integrating online learning into VFL presents challenges due to the unique nature of VFL, where clients possess non-intersecting feature sets for the same sample. In real-world scenarios, the clients may not receive data streaming for the disjoint features for the same entity synchronously. Instead, the data are typically generated by an \emph{event} relevant to only a subset of clients. We are the first to identify these challenges in online VFL, which have been overlooked by previous research. To address these challenges, we proposed an event-driven online VFL framework. In this framework, only a subset of clients were activated during each event, while the remaining clients passively collaborated in the learning process. Furthermore, we incorporated \emph{dynamic local regret (DLR)} into VFL to address the challenges posed by online learning problems with non-convex models within a non-stationary environment. We conducted a comprehensive regret analysis of our proposed framework, specifically examining the DLR under non-convex conditions with event-driven online VFL. Extensive experiments demonstrated that our proposed framework was more stable than the existing online VFL framework under non-stationary data conditions while also significantly reducing communication and computation costs.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Online Vertical Federated Learning for Cooperative Spectrum SensingIEEE Transactions on Cognitive Communications and Networking, 2024
- Distributed learning with compressed gradient differencesOptimization Methods and Software, 2024
- Secure and fast asynchronous Vertical Federated Learning via cascaded hybrid optimizationMachine Learning, 2024
- A Hybrid Self-Supervised Learning Framework for Vertical Federated LearningIEEE Transactions on Big Data, 2024
- Tighter Regret Analysis and Optimization of Online Federated LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Online Federated Learning via Non-Stationary Detection and Adaptation Amidst Concept DriftIEEE/ACM Transactions on Networking, 2023
- Vertical Federated Edge Learning With Distributed Integrated Sensing and CommunicationIEEE Communications Letters, 2022
- Communication-Efficient Randomized Algorithm for Multi-Kernel Online Federated LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Federated Learning With Differential Privacy: Algorithms and Performance AnalysisIEEE Transactions on Information Forensics and Security, 2020
- Extracting certainty from uncertainty: regret bounded by variation in costsMachine Learning, 2010