Pith. sign in

REVIEW 11 cited by

HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients

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 2010.01264 v3 pith:5UUKSKRS submitted 2020-10-03 cs.LG stat.ML

Enmao Diao , Jie Ding , Vahid Tarokh This is my paper
classification cs.LGstat.ML
keywords computationclientsheterogeneouslearningcommunicationfederatedmodelmodels
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Federated Learning (FL) is a method of training machine learning models on private data distributed over a large number of possibly heterogeneous clients such as mobile phones and IoT devices. In this work, we propose a new federated learning framework named HeteroFL to address heterogeneous clients equipped with very different computation and communication capabilities. Our solution can enable the training of heterogeneous local models with varying computation complexities and still produce a single global inference model. For the first time, our method challenges the underlying assumption of existing work that local models have to share the same architecture as the global model. We demonstrate several strategies to enhance FL training and conduct extensive empirical evaluations, including five computation complexity levels of three model architecture on three datasets. We show that adaptively distributing subnetworks according to clients' capabilities is both computation and communication efficient.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

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

  1. Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Gradient clipping eliminates the dependence on maximum delay in the oracle complexity of asynchronous SGD, yielding convergence in expectation and high probability under sub-Weibull gradient noise.

  2. Rashomon Sets and Model Multiplicity in Federated Learning

    cs.LG 2026-02 unverdicted novelty 7.0 of 10

    The work provides the first formal definitions of Rashomon sets for federated learning and introduces a multiplicity-aware training pipeline evaluated on standard benchmarks.

  3. H2Tune: Federated Foundation Model Fine-Tuning with Hybrid Heterogeneity

    cs.LG 2025-07 conditional novelty 6.0 of 10

    H2Tune enables federated fine-tuning across heterogeneous foundation models by sharing sparsified rank-aligned middle matrices with learned layer mappings and alternating shared/private updates.

  4. Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

    cs.LG 2026-07 conditional novelty 5.5 of 10

    Collate jointly trains heterogeneous models under per-device latency constraints via dynamic zeroizing-recovering and proto-corrected aggregation, gaining ~2–3% accuracy over prior heterogeneous FL.

  5. HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    HASA computes client heterogeneity scores from local data and assigns wider subnets to less heterogeneous clients, raising mean client test accuracy from 13.82% to 14.32% and improving worst-client accuracy versus uni...

  6. FedPLT: Scalable, Resource-Efficient, and Heterogeneity-Aware Federated Learning via Partial Layer Training

    cs.DC 2026-05 unverdicted novelty 5.0 of 10

    FedPLT assigns client-specific model layers for training and matches or beats full-model federated learning accuracy with 71-82 percent fewer trainable parameters per client.

  7. Representation-Aligned Multi-Scale Personalization for Federated Learning

    cs.LG 2026-04 unverdicted novelty 5.0 of 10

    FRAMP generates client-specific models from compact descriptors in federated learning, trains tailored submodels, and aligns representations to balance personalization with global consistency.

  8. Semantic-based Distributed Learning for Diverse and Discriminative Representations

    cs.LG 2026-04 unverdicted novelty 4.0 of 10

    A new distributed optimization method enforces diverse and discriminative representations via variance constraints for i.i.d. data and node clustering for non-i.i.d. data, with theoretical guarantees and semantic sharing.

  9. Enabling Federated Object Detection for Connected Autonomous Vehicles: A Deployment-Oriented Evaluation

    cs.CV 2025-09 conditional novelty 4.0 of 10

    Federated YOLO and Deformable DETR detectors are evaluated for CAVs on KITTI, BDD100K, and nuScenes, with resource profiling under non-IID splits, client dropout, and weather and lighting shifts.

  10. Heterogeneous Federated Learning with Prototype Alignment and Upscaling

    cs.LG 2025-07 conditional novelty 3.0 of 10

    ProtoNorm adds server-side prototype alignment and a per-dataset scaling factor to FedProto-style federated learning, improving accuracy but with the gain largely driven by the tuned scaling factor.

  11. Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions

    cs.LG 2024-06 unverdicted novelty 2.0 of 10

    A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.

Pith tools