mlsanityData to 14 Oct 2026

FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences

arXiv 2210.08450 ↗First posted 16 Oct 2022cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Due to user privacy and regulatory restrictions, federate learning (FL) is proposed as a distributed learning framework for training deep neural networks (DNN) on decentralized data clients. Recent advancements in FL have applied Neural Architecture Search (NAS) to replace the predefined one-size-fit-all DNN model, which is not optimal for all tasks of various data distributions, with searchable DNN architectures. However, previous methods suffer from expensive communication cost rasied by frequent large model parameters transmission between the server and clients. Such difficulty is further amplified when combining NAS algorithms, which commonly require prohibitive computation and enormous model storage. Towards this end, we propose FAQS, an efficient personalized FL-NAS-Quantization framework to reduce the communication cost with three features: weight-sharing super kernels, bit-sharing quantization and masked transmission. FAQS has an affordable search time and demands very limited size of transmitted messages at each round. By setting different personlized pareto function loss on local clients, FAQS can yield heterogeneous hardware-aware models for various user preferences. Experimental results show that FAQS achieves average reduction of 1.58x in communication bandwith per round compared with normal FL framework and 4.51x compared with FL+NAS framwork.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 25 references that are in the map. First posted on arXiv 16 Oct 2022.

Builds on

23 of 25 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  5. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  7. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  8. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  9. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  10. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
  11. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  12. 2017Genetic CNNcited by 124
11 more
  1. 2019Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hourscited by 87
  2. 2020DSNAS: Direct Neural Architecture Search without Parameter Retrainingcited by 69
  3. 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 57
  4. 2020EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutionscited by 36
  5. 2018BlockQNN: Efficient Block-wise Neural Network Architecture Generationcited by 31
  6. 2020Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Searchcited by 30
  7. 2020Real-time Federated Evolutionary Neural Architecture Searchcited by 20
  8. 2019On Neural Architecture Search for Resource-Constrained Hardware Platformscited by 18
  9. 2018Joint Neural Architecture Search and Quantizationcited by 13
  10. 2020Differentially-private Federated Neural Architecture Searchcited by 9
  11. 2020Direct Federated Neural Architecture Searchcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Optimized Federated Knowledge Distillation with Distributed Neural Architecture Search
  2. 2025Enhancing Communication Efficiency in FL with Adaptive Gradient Quantization and Communication Frequency Optimization
  3. 2025FedHQ: Hybrid Runtime Quantization for Federated Learning
  4. 2021FedHe: Heterogeneous Models and Communication-Efficient Federated Learning
  5. 2022How to Attain Communication-Efficient DNN Training? Convert, Compress, Correct
  6. 2022FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers
  7. 2024FedFQ: Federated Learning with Fine-Grained Quantization
  8. 2026FANS: Federated Adaptive Network Search Learning for Heterogeneous Devices