Litcius/Paper detail

VFL+: Low-Coupling Vertical Federated Learning With Privileged Information Paradigm

Wei Dai, Teng Cui, Tong Zhang, Badong Chen

2025IEEE Transactions on Emerging Topics in Computational Intelligence6 citationsDOI

Abstract

Vertical Federated Learning (VFL) enables the construction of models by combining clients with different features without compromising privacy. Existing VFL methods exhibit tightly coupled participant parameters, resulting in substantial interdependencies among clients during the prediction phase, which significantly hampers the model's usability. To tackle these challenges, this paper studies a VFL approach with low coupling of parameters between clients. Drawing inspiration from federated cooperation and teacher-supervised learning, we propose a low-coupling vertical federated learning with privileged information paradigm (VFL+), allowing participants to make autonomous predictions. Specifically, VFL+ treats information from other clients as privileged data during the training phase rather than the testing phase, thereby achieving independence in individual model predictions. Subsequently, this paper further investigates three typical scenarios of vertical cooperation and designs corresponding cooperative frameworks. Systematic experiments on real data sets demonstrate the effectiveness of the proposed method.

Topics & Concepts

Computer scienceParadigm shiftData scienceCognitive scienceHuman–computer interactionCognitive psychologyPsychologyEpistemologyPhilosophyPrivacy-Preserving Technologies in DataStochastic Gradient Optimization TechniquesRecommender Systems and Techniques
VFL+: Low-Coupling Vertical Federated Learning With Privileged Information Paradigm | Litcius