Pith. sign in

REVIEW 4 cited by

FedMix: Approximation of Mixup under Mean Augmented Federated Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2107.00233 v1 pith:URCJPOX4 submitted 2021-07-01 cs.LG cs.AIcs.CVcs.DC

Tehrim Yoon , Sumin Shin , Sung Ju Hwang , Eunho Yang This is my paper · ORCID
classification cs.LGcs.AIcs.CVcs.DC
keywords datafederatedlocalunderlearningalgorithmsaugmentationaugmented
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated learning (FL) allows edge devices to collectively learn a model without directly sharing data within each device, thus preserving privacy and eliminating the need to store data globally. While there are promising results under the assumption of independent and identically distributed (iid) local data, current state-of-the-art algorithms suffer from performance degradation as the heterogeneity of local data across clients increases. To resolve this issue, we propose a simple framework, Mean Augmented Federated Learning (MAFL), where clients send and receive averaged local data, subject to the privacy requirements of target applications. Under our framework, we propose a new augmentation algorithm, named FedMix, which is inspired by a phenomenal yet simple data augmentation method, Mixup, but does not require local raw data to be directly shared among devices. Our method shows greatly improved performance in the standard benchmark datasets of FL, under highly non-iid federated settings, compared to conventional algorithms.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning

    cs.LG 2024-12 conditional novelty 6.0 of 10

    FedCFA replaces local latent factors with global average features to generate counterfactual samples, improving federated global model accuracy under heterogeneous data.

  2. One-shot Federated Learning via Synthetic Distiller-Distillate Communication

    cs.LG 2024-12 conditional novelty 6.0 of 10

    FedSD2C beats prior one-shot federated learning baselines on ImageNette, Tiny-ImageNet, and OpenImage by sending compact latent codes of selected, Fourier-perturbed images instead of local models.

  3. UniVarFL: Uniformity and Variance Regularized Federated Learning for Heterogeneous Data

    cs.LG 2025-06 reject novelty 4.0 of 10

    UniVarFL adds a classifier variance regularizer and a hyperspherical uniformity regularizer to local federated training, reporting improved accuracy on some non-IID benchmarks but not consistently across its own experiments.

  4. FedAlign: Federated Domain Generalization with Cross-Client Feature Alignment

    cs.LG 2025-01 reject novelty 4.0 of 10

    FedAlign reports state-of-the-art average accuracy on PACS, OfficeHome, Office-Caltech-10, and miniDomainNet by combining MixStyle augmentation with supervised contrastive and prediction alignment losses.

Pith tools