Pith. sign in

REVIEW 5 cited by

Federated Learning with Matched Averaging

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 2002.06440 v1 pith:OUVH2Z2A submitted 2020-02-15 cs.LG stat.ML

Hongyi Wang , Mikhail Yurochkin , Yuekai Sun , Dimitris Papailiopoulos , Yasaman Khazaeni This is my paper
classification cs.LGstat.ML
keywords federatedlearningaveragingfedmamodelarchitecturesdatahidden
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated learning allows edge devices to collaboratively learn a shared model while keeping the training data on device, decoupling the ability to do model training from the need to store the data in the cloud. We propose Federated matched averaging (FedMA) algorithm designed for federated learning of modern neural network architectures e.g. convolutional neural networks (CNNs) and LSTMs. FedMA constructs the shared global model in a layer-wise manner by matching and averaging hidden elements (i.e. channels for convolution layers; hidden states for LSTM; neurons for fully connected layers) with similar feature extraction signatures. Our experiments indicate that FedMA not only outperforms popular state-of-the-art federated learning algorithms on deep CNN and LSTM architectures trained on real world datasets, but also reduces the overall communication burden.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Neural networks admit large families of approximately equivalent solutions via neuron identifiability even without structural symmetry, enabling linear low-loss merging paths without prior alignment.

  2. Flat Channels to Infinity in Neural Loss Landscapes

    cs.LG 2025-06 unverdicted novelty 7.0 of 10

    Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.

  3. Robust Federated Learning Under Real-World Client Churn

    cs.LG 2026-07 conditional novelty 6.0 of 10

    FeLiX reduces wall-clock time-to-target accuracy in federated learning by up to 2.37x using lightweight availability tiers, fresh-utility client selection, and informativeness-aware aggregation without requiring oracu...

  4. Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware

    quant-ph 2026-05 unverdicted novelty 6.0 of 10

    Q-RAIL derives effective noise budgets from backend metadata and transpiled circuits to produce stabilized aggregation weights for heterogeneous QFL, yielding +10 accuracy points over FedAvg on MNIST under hardware skew.

  5. Cyst-X: A Multi-Center MRI Benchmark and Federated Learning Framework for Malignancy-Risk Stratification of Pancreatic Cystic Neoplasm

    eess.IV 2025-07 conditional novelty 6.0 of 10

    A multi-center MRI benchmark and federated learning framework for IPMN malignancy-risk stratification, with an internal AUC of 0.85 on T2-weighted MRI.

Pith tools