Journal article · 2026 · Open access

D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning

Zhongchi Wang, Zhengyang Zhao, Hailong Sun

IEEE Transactions on Cognitive Communications and Networking, 12, 11817–11830 · Published 1 January 2026 · DOI 10.1109/tccn.2026.3727464

Open full textCite this paper

In brief

“D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning” is a 2026 journal article by Zhongchi Wang and 2 co-authors, published in IEEE Transactions on Cognitive Communications and Networking. 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 Cognitive Communications and Networking.

Citations
0
References
41
Authors
3

Abstract

Accurate client contribution evaluation is critical for sustainable federated learning and incentive design, yet existing methods face a trade-off between trust, complexity, and robustness. We show that validation-free, similarity-based metrics can suffer from a federated noise coupling effect, where historical low-quality updates become entangled with the global trajectory, causing evaluation noise to accumulate and manifest as systematic bias across rounds. We proposeD3em, a dual-layer dynamic debiasing mechanism built on a parallel local–federated dual-model training framework.D3emextracts a noise-decoupled independent value from the local branch and a collaborative value from the federated branch, and fuses them via a phase-aware weighting schedule to stabilize contribution scores throughout training. Experiments on CIFAR-10, Fashion-MNIST, and SST-5 under diverse heterogeneous partitions show thatD3emimproves global accuracy by 6.15 percentage points on average over representative baselines, and achieves an average fairness of 97.08% when coupled with incentive schemes. Meanwhile,D3emachieves comparable or even better end-to-end overhead in terms of total communication and total latency. The code is available athttps://anonymous.4open.science/r/D_3AM-8A70

Cite this paper

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

APA 7

Wang, Z., Zhao, Z., & Sun, H. (2026). D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning. IEEE Transactions on Cognitive Communications and Networking, 12, 11817–11830. https://doi.org/10.1109/tccn.2026.3727464

MLA 9

Wang, Zhongchi, et al. “D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning.” IEEE Transactions on Cognitive Communications and Networking, vol. 12, 2026, pp. 11817–11830. https://doi.org/10.1109/tccn.2026.3727464.

Chicago

Wang, Zhongchi, Zhengyang Zhao, and Hailong Sun. 2026. “D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning.” IEEE Transactions on Cognitive Communications and Networking 12: 11817–11830. https://doi.org/10.1109/tccn.2026.3727464.

Harvard

Wang, Z., Zhao, Z. and Sun, H. (2026) ‘D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning’, IEEE Transactions on Cognitive Communications and Networking, 12, pp. 11817–11830. doi:10.1109/tccn.2026.3727464.

IEEE

Z. Wang, Z. Zhao, and H. Sun, “D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning,” IEEE Transactions on Cognitive Communications and Networking, vol. 12, pp. 11817–11830, 2026, doi: 10.1109/tccn.2026.3727464.

BibTeX

@article{wang2026dual,
  title     = {{D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning}},
  author    = {Wang, Zhongchi and Zhao, Zhengyang and Sun, Hailong},
  journal   = {IEEE Transactions on Cognitive Communications and Networking},
  year      = {2026},
  volume    = {12},
  pages     = {11817--11830},
  doi       = {10.1109/tccn.2026.3727464},
  url       = {https://doi.org/10.1109/tccn.2026.3727464}
}

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
  • incentive design
  • noise coupling
  • evaluation bias
  • fairness
  • communication efficiency

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?

Wang, Z., Zhao, Z., & Sun, H. (2026). D 3 em: A Dual-Layer Dynamic Debiasing Evaluation Mechanism for Client Contribution in Federated Learning. IEEE Transactions on Cognitive Communications and Networking, 12, 11817–11830. https://doi.org/10.1109/tccn.2026.3727464

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 Cognitive Communications and Networking: sign in and open the full text from this page.

Who wrote this paper?

Zhongchi Wang, Zhengyang Zhao, Hailong Sun.

What is the DOI of this paper?

10.1109/tccn.2026.3727464, permanently at https://doi.org/10.1109/tccn.2026.3727464. 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.