Pith. sign in

REVIEW 1 cited by

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2303.00250 v1 pith:OSAKZN55 submitted 2023-03-01 cs.LG

classification cs.LG
keywords federatedadversariallearningtrainingheterogeneitysfatdataframework
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models. However, the straightforward combination between adversarial training and federated learning in one framework can lead to the undesired robustness deterioration. We discover that the attribution behind this phenomenon is that the generated adversarial data could exacerbate the data heterogeneity among local clients, making the wrapped federated learning perform poorly. To deal with this problem, we propose a novel framework called Slack Federated Adversarial Training (SFAT), assigning the client-wise slack during aggregation to combat the intensified heterogeneity. Theoretically, we analyze the convergence of the proposed method to properly relax the objective when combining federated learning and adversarial training. Experimentally, we verify the rationality and effectiveness of SFAT on various benchmarked and real-world datasets with different adversarial training and federated optimization methods. The code is publicly available at https://github.com/ZFancy/SFAT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. How Does the Smoothness Approximation Method Facilitate Generalization for Federated Adversarial Learning?

    cs.LG 2024-12 reject novelty 6.0 of 10

    Generalization bounds are derived for federated adversarial learning under three smoothing methods, with randomized smoothing claimed best and the SFAL reweighting claimed to improve generalization.

Pith tools