Pith. sign in

REVIEW 14 cited by

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

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 1811.11479 v2 pith:R45UJYHU submitted 2018-11-28 cs.LG cs.NIstat.ML

Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data

classification cs.LG cs.NIstat.ML
keywords datafederatedcommunicationlearningmodelaugmentationcompareddataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

On-device machine learning (ML) enables the training process to exploit a massive amount of user-generated private data samples. To enjoy this benefit, inter-device communication overhead should be minimized. With this end, we propose federated distillation (FD), a distributed model training algorithm whose communication payload size is much smaller than a benchmark scheme, federated learning (FL), particularly when the model size is large. Moreover, user-generated data samples are likely to become non-IID across devices, which commonly degrades the performance compared to the case with an IID dataset. To cope with this, we propose federated augmentation (FAug), where each device collectively trains a generative model, and thereby augments its local data towards yielding an IID dataset. Empirical studies demonstrate that FD with FAug yields around 26x less communication overhead while achieving 95-98% test accuracy compared to FL.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

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

  1. TallyTrain: Communication-Efficient Federated Distillation

    cs.LG 2026-06 unverdicted novelty 7.0

    TallyTrain is a hard-label distillation protocol for federated learning that uses argmax transmission and optional sparse merges to match soft-label performance at up to 1000x lower communication cost.

  2. Quantifying and Defending against the Privacy Risk in Logit-based Federated Learning

    cs.CR 2026-06 unverdicted novelty 7.0

    Logit-based federated learning leaks private model information to a semi-honest server via shared logits even with unrelated public data, enabling an adaptive stealing attack with theoretical bounds and a logit-pertur...

  3. From Coordinate Matching to Structural Alignment: Rethinking Prototype Alignment in Heterogeneous Federated Learning

    cs.AI 2026-05 unverdicted novelty 7.0

    FedSAF shifts prototype alignment in heterogeneous federated learning from coordinate matching to inter-class structural relations and reports up to 3.52% gains over prior methods.

  4. Enhancing Visual Representation with Textual Semantics: Textual Semantics-Powered Prototypes for Heterogeneous Federated Learning

    cs.LG 2025-03 unverdicted novelty 7.0

    FedTSP builds class prototypes from LLM-generated text descriptions via PLMs and trainable prompts to preserve semantic relationships and reduce heterogeneity effects in federated learning.

  5. Function-Space ADMM for Decentralized Federated Learning: A Control Theoretic Perspective

    cs.LG 2026-05 unverdicted novelty 6.0

    FedF-ADMM uses function-space ADMM updates projected via knowledge distillation plus a PI-like stabilization term to deliver faster, more stable convergence and higher accuracy than prior decentralized FL methods unde...

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

    cs.LG 2026-07 conditional novelty 5.5

    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.

  7. Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search

    cs.LG 2026-05 unverdicted novelty 5.0

    FedKDNAS combines client-side neural architecture search with knowledge distillation from aggregated server predictions to improve accuracy and efficiency in heterogeneous federated learning.

  8. BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring

    cs.AI 2026-05 unverdicted novelty 5.0

    BiFedKD improves ECG classification accuracy by 3.52% and Macro-F1 by 9.93% on MIT-BIH while cutting communication overhead 40% and computation cost 71.7% versus baseline federated methods.

  9. PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

    cs.LG 2026-04 unverdicted novelty 5.0

    PubSwap uses a small public dataset for selective off-policy response swapping in federated RLVR to improve coordination and performance over standard baselines on math and medical reasoning tasks.

  10. Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data

    cs.LG 2025-08 unverdicted novelty 5.0

    EdgeFD uses a KMeans-based client-side filter to improve federated distillation accuracy close to IID levels on non-IID data distributions for resource-constrained edge devices.

  11. Multi-hop Federated Private Data Augmentation with Sample Compression

    cs.LG 2019-07 unverdicted novelty 4.0

    MultFAug combines multi-hop relaying and sample compression in federated settings to enhance privacy guarantees, cut transmission delay, and raise local training performance on non-IID data.

  12. Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions

    cs.ET 2026-04 unverdicted novelty 2.0

    The paper provides a structured overview of IoE concepts, components, architectures, enabling technologies, challenges, and open research directions for 6G-enabled systems.

  13. Internet of Everything in the 6G Era: Paradigms, Enablers, Potentials and Future Directions

    cs.ET 2026-04 unverdicted novelty 2.0

    The paper provides a structured overview of IoE concepts, components, architectures, enabling technologies, challenges, and open research directions for 6G-enabled IoE systems.

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

    cs.LG 2024-06 unverdicted novelty 2.0

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