mlsanityData to 14 Oct 2026

Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling

arXiv 2212.14760 ↗First posted 30 Dec 2022cs.LG cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 21 references that are in the map. First posted on arXiv 30 Dec 2022.

Builds on

9 of 21 references.

References · 9

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  6. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  7. 2017TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learningcited by 256
  8. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  9. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021FedDQ: Communication-Efficient Federated Learning with Descending Quantization
  2. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learning
  3. 2022FedVQCS: Federated Learning via Vector Quantized Compressed Sensing
  4. 2021Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design
  5. 2024Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes
  6. 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning
  7. 2024FedFQ: Federated Learning with Fine-Grained Quantization
  8. 2022Online Model Compression for Federated Learning with Large Models