FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift

TL;DR

FedPall introduces a prototype-based adversarial and collaborative learning framework to address feature drift in federated learning, improving model performance on heterogeneous, feature-drifted datasets.

Contribution

The paper proposes FedPall, a novel federated learning framework that unifies feature spaces and enhances classification through prototype-based adversarial and collaborative learning.

Findings

FedPall outperforms existing methods on feature-drifted datasets.

It effectively unifies feature spaces across clients.

Demonstrates superior classification accuracy in federated settings with feature heterogeneity.

Abstract

Federated learning (FL) enables collaborative training of a global model in the centralized server with data from multiple parties while preserving privacy. However, data heterogeneity can significantly degrade the performance of the global model when each party uses datasets from different sources to train a local model, thereby affecting personalized local models. Among various cases of data heterogeneity, feature drift, feature space difference among parties, is prevalent in real-life data but remains largely unexplored. Feature drift can distract feature extraction learning in clients and thus lead to poor feature extraction and classification performance. To tackle the problem of feature drift in FL, we propose FedPall, an FL framework that utilizes prototype-based adversarial learning to unify feature spaces and collaborative learning to reinforce class information within the features. Moreover, FedPall leverages mixed features generated from global prototypes and local features to enhance the global classifier with classification-relevant information from a global perspective. Evaluation results on three representative feature-drifted datasets demonstrate FedPall's consistently superior performance in classification with feature-drifted data in the FL scenario.