FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

TL;DR

FedDAG introduces an adversarial framework in federated learning to generate diverse, novel medical image domains, significantly improving the global model's ability to generalize to unseen data.

Contribution

The paper proposes FedDAG, a novel federated domain adversarial generation method that enhances medical image analysis by simulating domain shifts and addressing client heterogeneity.

Findings

FedDAG improves generalization across four medical benchmarks.

Hierarchical aggregation mitigates client data heterogeneity.

Adversarial generation enhances model robustness to unseen domains.

Abstract

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model's generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG's ability to enhance generalization in federated medical scenarios.