# Bitwidth Heterogeneous Federated Learning with Progressive Weight Dequantization

arXiv: https://arxiv.org/abs/2202.11453 · HTML: https://mlsanity.com/paper/2202.11453/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://mlsanity.com/paper/1909.13014/) (2019)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [Personalized Federated Learning: A Meta-Learning Approach](https://mlsanity.com/paper/2002.07948/) (2020)
- [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://mlsanity.com/paper/1909.12488/) (2019)
- [TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning](https://mlsanity.com/paper/1705.07878/) (2017)
- [Ternary Weight Networks](https://mlsanity.com/paper/1605.04711/) (2016)
- [Federated Continual Learning with Weighted Inter-client Transfer](https://mlsanity.com/paper/2003.03196/) (2020)
- [Federated Learning with Compression: Unified Analysis and Sharp Guarantees](https://mlsanity.com/paper/2007.01154/) (2020)
- [Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning](https://mlsanity.com/paper/2006.12097/) (2020)
- [Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation](https://mlsanity.com/paper/1903.07424/) (2019)
- [Invertible Image Signal Processing](https://mlsanity.com/paper/2103.15061/) (2021)
- [Training and Inference with Integers in Deep Neural Networks](https://mlsanity.com/paper/1802.04680/) (2018)
- [Towards Unified INT8 Training for Convolutional Neural Network](https://mlsanity.com/paper/1912.12607/) (2019)
- [DenseNet: Implementing Efficient ConvNet Descriptor Pyramids](https://mlsanity.com/paper/1404.1869/) (2014)
- [Distribution Adaptive INT8 Quantization for Training CNNs](https://mlsanity.com/paper/2102.04782/) (2021)
- [FleXOR: Trainable Fractional Quantization](https://mlsanity.com/paper/2009.04126/) (2020)
- [Closing the Dequantization Gap: PixelCNN as a Single-Layer Flow](https://mlsanity.com/paper/2002.02547/) (2020)

## Built on by (most cited first, 11 of 11)

- [Heterogeneous Federated Learning: State-of-the-art and Research Challenges](https://mlsanity.com/paper/2307.10616/) (2023)
- [Conformal Prediction for Federated Uncertainty Quantification Under Label Shift](https://mlsanity.com/paper/2306.05131/) (2023)
- [Recurrent Early Exits for Federated Learning with Heterogeneous Clients](https://mlsanity.com/paper/2405.14791/) (2024)
- [Mixed-Precision Quantization for Federated Learning on Resource-Constrained Heterogeneous Devices](https://mlsanity.com/paper/2311.18129/) (2023)
- [A Comprehensive Survey of Federated Transfer Learning: Challenges, Methods and Applications](https://mlsanity.com/paper/2403.01387/) (2024)
- [NeFL: Nested Model Scaling for Federated Learning with System Heterogeneous Clients](https://mlsanity.com/paper/2308.07761/) (2023)
- [Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity](https://mlsanity.com/paper/2312.13380/) (2023)
- [Towards Federated Learning with On-device Training and Communication in 8-bit Floating Point](https://mlsanity.com/paper/2407.02610/) (2024)
- [FedShift: Robust Federated Learning Aggregation Scheme in Resource Constrained Environment via Weight Shifting](https://mlsanity.com/paper/2402.01070/) (2024)
- [Photon: Federated LLM Pre-Training](https://mlsanity.com/paper/2411.02908/) (2024)
- [QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation](https://mlsanity.com/paper/2607.22743/) (2026)

## Abstract (arXiv)

In practical federated learning scenarios, the participating devices may have different bitwidths for computation and memory storage by design. However, despite the progress made in device-heterogeneous federated learning scenarios, the heterogeneity in the bitwidth specifications in the hardware has been mostly overlooked. We introduce a pragmatic FL scenario with bitwidth heterogeneity across the participating devices, dubbed as Bitwidth Heterogeneous Federated Learning (BHFL). BHFL brings in a new challenge, that the aggregation of model parameters with different bitwidths could result in severe performance degeneration, especially for high-bitwidth models. To tackle this problem, we propose ProWD framework, which has a trainable weight dequantizer at the central server that progressively reconstructs the low-bitwidth weights into higher bitwidth weights, and finally into full-precision weights. ProWD further selectively aggregates the model parameters to maximize the compatibility across bit-heterogeneous weights. We validate ProWD against relevant FL baselines on the benchmark datasets, using clients with varying bitwidths. Our ProWD largely outperforms the baseline FL algorithms as well as naive approaches (e.g. grouped averaging) under the proposed BHFL scenario.