FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning

TL;DR

FedGTST enhances federated learning transferability by tuning Jacobian statistics, improving global model performance across diverse datasets while preserving privacy and reducing domain discrepancy.

Contribution

The paper introduces FedGTST, a novel federated learning algorithm that uses Jacobian norm statistics to improve global transferability and reduce variance across clients.

Findings

FedGTST outperforms baselines like FedSR and FedIIR in accuracy.

Increasing average Jacobian norm improves target loss control.

Reducing Jacobian variance enhances transferability across domains.

Abstract

The performance of Transfer Learning (TL) heavily relies on effective pretraining, which demands large datasets and substantial computational resources. As a result, executing TL is often challenging for individual model developers. Federated Learning (FL) addresses these issues by facilitating collaborations among clients, expanding the dataset indirectly, distributing computational costs, and preserving privacy. However, key challenges remain unresolved. First, existing FL methods tend to optimize transferability only within local domains, neglecting the global learning domain. Second, most approaches rely on indirect transferability metrics, which do not accurately reflect the final target loss or true degree of transferability. To address these gaps, we propose two enhancements to FL. First, we introduce a client-server exchange protocol that leverages cross-client Jacobian (gradient) norms to boost transferability. Second, we increase the average Jacobian norm across clients at the server, using this as a local regularizer to reduce cross-client Jacobian variance. Our transferable federated algorithm, termed FedGTST (Federated Global Transferability via Statistics Tuning), demonstrates that increasing the average Jacobian and reducing its variance allows for tighter control of the target loss. This leads to an upper bound on the target loss in terms of the source loss and source-target domain discrepancy. Extensive experiments on datasets such as MNIST to MNIST-M and CIFAR10 to SVHN show that FedGTST outperforms relevant baselines, including FedSR. On the second dataset pair, FedGTST improves accuracy by 9.8% over FedSR and 7.6% over FedIIR when LeNet is used as the backbone.