CalFAT: Calibrated Federated Adversarial Training with Label Skewness

Xingjun Ma, Chen Chen, Lingjuan Lyu, Yuchen Liu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• cc233/calfat — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent studies have shown that, like traditional machine learning, federated learning (FL) is also vulnerable to adversarial attacks. To improve the adversarial robustness of FL, federated adversarial training (FAT) methods have been proposed to apply adversarial training locally before global aggregation. Although these methods demonstrate promising results on independent identically distributed (IID) data, they suffer from training instability on non-IID data with label skewness, resulting in degraded natural accuracy. This tends to hinder the application of FAT in real-world applications where the label distribution across the clients is often skewed. In this paper, we study the problem of FAT under label skewness, and reveal one root cause of the training instability and natural accuracy degradation issues: skewed labels lead to non-identical class probabilities and heterogeneous local models. We then propose a Calibrated FAT (CalFAT) approach to tackle the instability issue by calibrating the logits adaptively to balance the classes. We show both theoretically and empirically that the optimization of CalFAT leads to homogeneous local models across the clients and better convergence points. Code is available at GitHub.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2205.14926")
get_code_for_paper("2205.14926")
have("2205.14926")

Connect an agent — have() is free.