Journal article · 2026 · Open access

Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel

Weiwei Li, Weiwei Li, Chao Ma, Athanasios V. Vasilakos, Yue Wang, Tao Wu, Wei Song, Jiannong Cao

IEEE Transactions on Mobile Computing, 25(11), 20641–20657 · Published 16 July 2026 · DOI 10.1109/tmc.2026.3713384

Open full textCite this paper

In brief

“Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel” is a 2026 journal article by Weiwei Li and 7 co-authors, published in IEEE Transactions on Mobile Computing. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Mobile Computing.

Citations
0
References
48
Authors
8

Abstract

Reducing the communication cost to alleviate the contradiction between the limited bandwidth and huge transmitted parameters in Federated Learning (FL) is a persisting challenge. Since the transmission parameters obtained by vanilla convolution primarily rely on the product of kernel and channels, recent works (e.g., Fed-KGF) reduce the transmission parameters by reducing the number of channels. While they ignore the impact of kernel elements on transmission efficiency. In this paper, we focus on reducing the density of convolutional kernel and innovatively propose a novel convolutional kernel, named Chessboard Convolutional Kernel (i.e.,Fed-ChessConv), to further significantly reduce the transmission parameters while maintaining the performance of the global model in FL. Given a kernel with$n\times n$size (i.e.,$n^{2}$elements within this kernel), we retain elements that are at even-row-even-column and odd-row-odd-column positions and discard the rest, forming a chessboard-like convolutional kernel with a size of$\lceil \frac{n^{2}}{2} \rceil$. Specifically, chessboard convolutional kernel extracts data features at the first step. Because of a chessboard convolutional kernel with size of$\lceil \frac{n^{2}}{2} \rceil$rather than$n\times n$, not all features are involved in extraction at the first step. However, those uninvolved features would be supplemently extracted at the second step after sliding the window for one stride. With the window sliding stride by stride on images, chessboard convolutional kernel extracts all features as the vanilla one does, with a stride of 1, while the number of the transmitted parameters is reduced by approximately 50%. We deploy one network with chessboard convolutional kernel to each client and the server in FL, and we transmit the updated parameters from clients to server. The performance of our chessboard convolutional kernel and the global model in ourFed-ChessConvhave been theoretically analyzed. Experimental results on both non-Independent and Identically Distributed (non-IID) and IID scenarios for image classification and object detection tasks demonstrate that ourFed-ChessConvoutperforms SOTA models.Fed-ChessConvachieves 3.4% (3.96%) higher classification accuracy and roughly 41.61% (96.91%) fewer transmission parameters on CIFAR-100, and presents similar detection performance with 42.51% (93.61%) fewer transmission parameters than the recent Fed-KGF (Fed-LTP) on COCO2017 datasets.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Li, W., Li, W., Ma, C., Vasilakos, A. V., Wang, Y., Wu, T., Song, W., & Cao, J. (2026). Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel. IEEE Transactions on Mobile Computing, 25(11), 20641–20657. https://doi.org/10.1109/tmc.2026.3713384

MLA 9

Li, Weiwei, et al. “Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel.” IEEE Transactions on Mobile Computing, vol. 25, no. 11, 2026, pp. 20641–20657. https://doi.org/10.1109/tmc.2026.3713384.

Chicago

Li, Weiwei, Weiwei Li, Chao Ma, Athanasios V. Vasilakos, Yue Wang, Tao Wu, Wei Song, and Jiannong Cao. 2026. “Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel.” IEEE Transactions on Mobile Computing 25 (11): 20641–20657. https://doi.org/10.1109/tmc.2026.3713384.

Harvard

Li, W. et al. (2026) ‘Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel’, IEEE Transactions on Mobile Computing, 25(11), pp. 20641–20657. doi:10.1109/tmc.2026.3713384.

IEEE

W. Li et al., “Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel,” IEEE Transactions on Mobile Computing, vol. 25, no. 11, pp. 20641–20657, 2026, doi: 10.1109/tmc.2026.3713384.

BibTeX

@article{li2026transmission,
  title     = {{Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel}},
  author    = {Li, Weiwei and Li, Weiwei and Ma, Chao and Vasilakos, Athanasios V. and Wang, Yue and Wu, Tao and Song, Wei and Cao, Jiannong},
  journal   = {IEEE Transactions on Mobile Computing},
  year      = {2026},
  volume    = {25},
  number    = {11},
  pages     = {20641--20657},
  doi       = {10.1109/tmc.2026.3713384},
  url       = {https://doi.org/10.1109/tmc.2026.3713384}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • federated learning
  • communication efficiency
  • non-IID data
  • image classification
  • object detection

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Li, W., Li, W., Ma, C., Vasilakos, A. V., Wang, Y., Wu, T., Song, W., & Cao, J. (2026). Transmission-Efficient Federated Learning via Chessboard Convolutional Kernel. IEEE Transactions on Mobile Computing, 25(11), 20641–20657. https://doi.org/10.1109/tmc.2026.3713384

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at IEEE Transactions on Mobile Computing: sign in and open the full text from this page.

Who wrote this paper?

Weiwei Li, Weiwei Li, Chao Ma, Athanasios V. Vasilakos, Yue Wang, Tao Wu, Wei Song, Jiannong Cao.

What is the DOI of this paper?

10.1109/tmc.2026.3713384, permanently at https://doi.org/10.1109/tmc.2026.3713384. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.