Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity

by   Zhuoning Yuan, et al.

eep UC (area under the ROC curve) aximization (DAM) has attracted much attention recently due to its great potential for imbalanced data classification. However, the research on ederated eep UC aximization (FDAM) is still limited. Compared with standard federated learning (FL) approaches that focus on decomposable minimization objectives, FDAM is more complicated due to its minimization objective is non-decomposable over individual examples. In this paper, we propose improved FDAM algorithms for heterogeneous data by solving the popular non-convex strongly-concave min-max formulation of DAM in a distributed fashion. A striking result of this paper is that the communication complexity of the proposed algorithm is a constant independent of the number of machines and also independent of the accuracy level, which improves an existing result by orders of magnitude. Of independent interest, the proposed algorithm can also be applied to a class of non-convex-strongly-concave min-max problems. The experiments have demonstrated the effectiveness of our FDAM algorithm on benchmark datasets, and on medical chest X-ray images from different organizations. Our experiment shows that the performance of FDAM using data from multiple hospitals can improve the AUC score on testing data from a single hospital for detecting life-threatening diseases based on chest radiographs.


page 1

page 2

page 3

page 4


Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks

In this paper, we study distributed algorithms for large-scale AUC maxim...

Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization

In this paper, we study multi-block min-max bilevel optimization problem...

Fast Objective and Duality Gap Convergence for Non-convex Strongly-concave Min-max Problems

This paper focuses on stochastic methods for solving smooth non-convex s...

Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications

The min-max problem, also known as the saddle point problem, is a class ...

SAGDA: Achieving 𝒪(ε^-2) Communication Complexity in Federated Min-Max Learning

To lower the communication complexity of federated min-max learning, a n...

Federated Compositional Deep AUC Maximization

Federated learning has attracted increasing attention due to the promise...

Resource-constrained Federated Edge Learning with Heterogeneous Data: Formulation and Analysis

Efficient collaboration between collaborative machine learning and wirel...

Please sign up or login with your details

Forgot password? Click here to reset