mlsanityData to 14 Oct 2026

Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference

arXiv 2603.15507 ↗First posted 16 Mar 2026cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) preserves privacy by distributing training across devices. However, using DNNs is computationally intensive at the low-powered edge during inference. Edge deployment demands models that simultaneously optimize memory footprint and computational efficiency, a dilemma where conventional DNNs fail by exceeding resource limits. Traditional post-training binarization reduces model size but suffers from severe accuracy loss due to quantization errors. To address these challenges, we propose FedBNN, a rotation-aware binary neural network framework that learns binary representations directly during local training. By encoding each weight as a single bit +1, -1 instead of a 32-bit float, FedBNN shrinks the model footprint, significantly reducing runtime (during inference) FLOPs and memory requirements in comparison to federated methods using real models. Evaluations across multiple benchmark datasets demonstrate that FedBNN significantly reduces resource consumption while performing similarly to existing federated methods using real-valued models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 21 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

14 of 21 references.

References · 14

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  4. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  5. 2020Rotated Binary Neural Networkcited by 77
  6. 2022Communication-Efficient Federated Learning with Accelerated Client Gradientcited by 24
  7. 2023FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregationcited by 22
  8. 2021Communication-Efficient Federated Learning with Binary Neural Networkscited by 14
  9. 2024SpaFL: Communication-Efficient Federated Learning with Sparse Models and Low computational Overheadcited by 9
  10. 2024FedBAT: Communication-Efficient Federated Learning via Learnable Binarizationcited by 9
  11. 2024Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysiscited by 8
  12. 2025The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learningcited by 5
2 more
  1. 2021Binarized ResNet: Enabling Robust Automatic Modulation Classification at the resource-constrained Edgecited by 3
  2. 2024Communication-Efficient Federated Group Distributionally Robust Optimizationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Energy and Memory-Efficient Federated Learning With Ordered Layer Freezing
  2. 2025FedBiF: Communication-Efficient Federated Learning via Bits Freezing
  3. 2022CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization
  4. 2023BAFFLE: A Baseline of Backpropagation-Free Federated Learning
  5. 2025FedSparQ: Adaptive Sparse Quantization with Error Feedback for Robust & Efficient Federated Learning
  6. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learning
  7. 2026CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge
  8. 2023Binary Federated Learning with Client-Level Differential Privacy