mlsanityData to 14 Oct 2026

DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting

arXiv 2608.05358 ↗First posted 5 Aug 2026cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated learning repeatedly incurs local optimization and model-update transmission. We study DG-FedReuse, a simulator-level mechanism that allows selected clients to contribute age-decayed cached updates when a stochastic head-gradient discrepancy proxy remains below a round-dependent threshold. A hard cache-age limit and minimum fresh-client quota constrain reuse, while fresh updates use an adaptive per-tensor Top-K numerical-field representation. Experiments cover six image-classification datasets, 50 virtual clients, Dirichlet label heterogeneity (α=0.5), and three seeds. At a common 90-round budget, DG-FedReuse yields 83.36-85.42% modeled update-data-field uplink saving, compared with 76.88% for matched Top-K FedAvg; the seed-aligned accuracy differences range from -5.29 to -0.14 percentage points. Best-observed test accuracies obtained under test-controlled checkpointing are retained only as exploratory archival evidence and range from -2.38 to +0.45 percentage points relative to matched FedAvg. A symmetric dense-model-downlink sensitivity reduces the headline saving to 41.68-F42.71% and the incremental gain over Top-K FedAvg to 3.24-4.27 percentage points, demonstrating the dependence of communication conclusions on the accounting boundary. The study characterizes the proposed reuse rule in the implemented simulator; it does not establish unbiased generalization, end-to-end bandwidth reduction, runtime or energy savings, faster convergence, or superiority over existing stale-update and lazy-aggregation methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 5 Aug 2026.

Builds on

19 of 27 references.

References · 19

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  7. 2020Adaptive Federated Optimizationcited by 1,046
  8. 2019Deep Leakage from Gradientscited by 1,021
  9. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  10. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  11. 2018Sparsified SGD with Memorycited by 376
  12. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
7 more
  1. 2021Fast Federated Learning in the Presence of Arbitrary Device Unavailabilitycited by 72
  2. 2022FedVARP: Tackling the Variance Due to Partial Client Participation in Federated Learningcited by 64
  3. 2023DoCoFL: Downlink Compression for Cross-Device Federated Learningcited by 28
  4. 20223PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregationcited by 27
  5. 2022GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexitycited by 18
  6. 2022Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank?cited by 16
  7. 2025Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learningcited by 1

Built on by

Not cited yet.