Pith. sign in

REVIEW 19 cited by

FedBN: Federated Learning on Non-IID Features via Local Batch Normalization

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 2102.07623 v2 pith:ZGGT4545 submitted 2021-02-15 cs.LG

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

The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of independent and identically distributed samples across local clients does not hold for federated learning setups. Under this setting, neural network training performance may vary significantly according to the data distribution and even hurt training convergence. Most of the previous work has focused on a difference in the distribution of labels or client shifts. Unlike those settings, we address an important problem of FL, e.g., different scanners/sensors in medical imaging, different scenery distribution in autonomous driving (highway vs. city), where local clients store examples with different distributions compared to other clients, which we denote as feature shift non-iid. In this work, we propose an effective method that uses local batch normalization to alleviate the feature shift before averaging models. The resulting scheme, called FedBN, outperforms both classical FedAvg, as well as the state-of-the-art for non-iid data (FedProx) on our extensive experiments. These empirical results are supported by a convergence analysis that shows in a simplified setting that FedBN has a faster convergence rate than FedAvg. Code is available at https://github.com/med-air/FedBN.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 19 Pith papers

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

  1. AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning

    cs.LG 2026-08 conditional novelty 6.0 of 10

    AS-FedBridge trains a shared pseudo-spike bridge so ANN and SNN clients in federated learning can align representations and improve collaborative accuracy.

  2. FM$^2$: Unified Federated Foundation Models for Heterogeneous Multimodal Medical Imaging

    cs.CV 2026-07 reject novelty 6.0 of 10

    FM² uses dual mixture-of-experts (per-class local, per-modality shared) with a proximal alignment regularizer to train federated medical imaging models across overlapped and disjoint modality settings, reporting consi...

  3. Benchmark Evaluation of Federated Learning on Multi-organ Images

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MobenFL is the broadest federated medical-imaging benchmark to date, pairing 20 algorithms with 22 multi-organ datasets and adding efficiency plus privacy metrics.

  4. Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity

    cs.LG 2026-04 conditional novelty 6.0 of 10

    Personalized local running-mean/variance observation normalization prevents weight-norm overshadowing in FedAvg and improves FedRL-PPO on heterogeneous MuJoCo morphology variants.

  5. AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt

    cs.LG 2025-12 unverdicted novelty 6.0 of 10

    AutoFed introduces a prompt-based personalized federated learning method that achieves superior traffic prediction performance on real-world datasets by sharing compact prompt matrices while preserving local specificity.

  6. AnalogFed: Privacy-Preserving Discovery of Analog Circuits at Scale with Federated Generative AI

    cs.LG 2025-07 reject novelty 6.0 of 10

    AnalogFed combines federated learning with a generative analog-topology model, adding dummy-token input perturbation and partial homomorphic encryption to resist membership inference and model inversion attacks.

  7. AFBS:Buffer Gradient Selection in Semi-asynchronous Federated Learning

    cs.LG 2025-06 conditional novelty 6.0 of 10

    AFBS scores buffered gradients by staleness and dataset size, discards low-value ones, and clusters clients through random-projection-encrypted label distributions before aggregation in semi-asynchronous federated learning.

  8. PathFL: Multi-Alignment Federated Learning for Pathology Image Segmentation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    PathFL combines image-level style exchange, feature-level mean/variance alignment, and layer-similarity aggregation to improve federated pathology image segmentation under cross-source, cross-modality, cross-organ, an...

  9. Hybrid Batch Normalisation: Resolving the Dilemma of Batch Normalisation in Federated Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Hybrid Batch Normalisation improves federated learning accuracy by combining local batch statistics with global statistics, and derives those global statistics from the pre-update global model.

  10. Multimodal Federated Learning: A Survey through the Lens of Different FL Paradigms

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A paradigm-based taxonomy of multimodal federated learning that assigns each branch a headline challenge: modality heterogeneity (horizontal), privacy leakage (vertical), and efficiency (hybrid).

  11. Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains

    cs.CV 2025-05 conditional novelty 5.0 of 10

    UAP, an alternating two-stage training protocol, improves unseen-domain accuracy in semi-supervised federated learning by aligning client and server features to a Gaussian distribution defined by the classifier weights.

  12. Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data

    cs.LG 2025-05 conditional novelty 5.0 of 10

    FedProj combines client-side gradient projection onto a global-knowledge loss with server-side ensemble distillation and outperforms existing federated learning methods on non-IID image and NLP benchmarks.

  13. Federated Deep Learning for Privacy-Preserving Cardiovascular Disease Risk Prediction

    cs.LG 2026-07 conditional novelty 4.0 of 10

    FedAvg DeepSurv across Lifelines (n=148k, self-report) and Rotterdam Study (n=10k, linked outcomes) raised C-statistics from 0.728 to 0.739 and 0.783 to 0.787 versus local training.

  14. Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning

    quant-ph 2025-09 reject novelty 4.0 of 10

    ADP-QFL adaptively adds client-level DP noise to QCNN federated updates, but its central variance-reduction theorem is not correctly derived and its non-convex convergence bound is vacuous.

  15. Federated Learning for Large Models in Medical Imaging: A Comprehensive Review

    cs.CR 2025-08 conditional novelty 4.0 of 10

    A survey of federated learning for medical imaging covers CT/MRI reconstruction and downstream diagnosis and segmentation, emphasizing non-IID data and privacy.

  16. Generalizable Federated Learning using Client Adaptive Focal Modulation

    cs.CV 2025-08 reject novelty 4.0 of 10

    The abstract describes AdaptFED, a claimed federated learning method, but the full text is an unrelated graph theory paper, so the claimed results are absent from the submission.

  17. Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift

    cs.CV 2025-07 reject novelty 4.0 of 10

    StaRFM reuses the authors' earlier CalShift penalties, extends them to 3D medical segmentation with patch-wise and voxel-wise variants, and claims large gains that are not consistently supported by the paper's own tables.

  18. Kuramoto-FedAvg: Using Synchronization Dynamics to Improve Federated Learning Optimization under Statistical Heterogeneity

    cs.LG 2025-05 reject novelty 4.0 of 10

    Kuramoto-FedAvg reweights client updates by their cosine similarity to the global update, but the paper's convergence bound is not derived and the empirical evidence is incomplete.

  19. Event-Driven Online Vertical Federated Learning

    cs.LG 2025-06

Pith tools