Journal article · 2026 · Open access

Adaptive Guidance for Local Training in Heterogeneous Federated Learning

Jianqing Zhang, Yang Liu, Hua Yang, Zhenzhe Zheng, Han Yu, Yuyin Zhou, Jian Cao, Qiang Yang

IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18 · Published 30 October 2026 · DOI 10.1109/tpami.2026.3748545

Open full textCite this paper

In brief

“Adaptive Guidance for Local Training in Heterogeneous Federated Learning” is a 2026 journal article by Jianqing Zhang and 7 co-authors, published in IEEE Transactions on Pattern Analysis and Machine Intelligence. OpenAlex counts 3 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE Transactions on Pattern Analysis and Machine Intelligence.

Citations
3
Most cited in
2026 (2)
Field-weighted impact
2.16
References
51
Authors
8

Abstract

Model heterogeneity poses a significant challenge in Heterogeneous Federated Learning (HtFL). In scenarios with diverse model architectures, directly aggregating model parameters is impractical, leading HtFL methods to incorporate an extra guiding objective alongside the original local objective on each client to facilitate collaboration. However, this often results in a mismatch between the guiding and local objectives. To resolve this mismatch and ensure the guiding objective consistently benefits each client's original objective rather than interfering with it, we propose Federated Learning-to-Guide (FedL2G), a federated method that adaptively learns to guide local training in a meta-learning manner. In this way, the client can learn the necessary knowledge from the process of aligning globally shared information, thereby compensating for the required information for its local task. We theoretically prove that FedL2G achieves a non-convex convergence rate of $\mathcal {O}(1/T)$. We also conduct extensive experiments across three types of data heterogeneity and six model heterogeneity settings, using 14 heterogeneous model architectures (e.g., CNNs and ViTs). The results show that FedL2G consistently outperforms 12 state-of-the-art methods in terms of test accuracy (both in-distribution and out-of-distribution) as well as communication and computational overhead, across standard benchmark datasets and specialized medical scenarios.

Cite this paper

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

APA 7

Zhang, J., Liu, Y., Yang, H., Zheng, Z., Yu, H., Zhou, Y., Cao, J., & Yang, Q. (2026). Adaptive Guidance for Local Training in Heterogeneous Federated Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3748545

MLA 9

Zhang, Jianqing, et al. “Adaptive Guidance for Local Training in Heterogeneous Federated Learning.” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, 2026, pp. 1–18. https://doi.org/10.1109/tpami.2026.3748545.

Chicago

Zhang, Jianqing, Yang Liu, Hua Yang, Zhenzhe Zheng, Han Yu, Yuyin Zhou, Jian Cao, and Qiang Yang. 2026. “Adaptive Guidance for Local Training in Heterogeneous Federated Learning.” IEEE Transactions on Pattern Analysis and Machine Intelligence PP: 1–18. https://doi.org/10.1109/tpami.2026.3748545.

Harvard

Zhang, J. et al. (2026) ‘Adaptive Guidance for Local Training in Heterogeneous Federated Learning’, IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, pp. 1–18. doi:10.1109/tpami.2026.3748545.

IEEE

J. Zhang et al., “Adaptive Guidance for Local Training in Heterogeneous Federated Learning,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PP, pp. 1–18, 2026, doi: 10.1109/tpami.2026.3748545.

BibTeX

@article{zhang2026adaptive,
  title     = {{Adaptive Guidance for Local Training in Heterogeneous Federated Learning}},
  author    = {Zhang, Jianqing and Liu, Yang and Yang, Hua and Zheng, Zhenzhe and Yu, Han and Zhou, Yuyin and Cao, Jian and Yang, Qiang},
  journal   = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year      = {2026},
  volume    = {PP},
  pages     = {1--18},
  doi       = {10.1109/tpami.2026.3748545},
  url       = {https://doi.org/10.1109/tpami.2026.3748545}
}

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

  • heterogeneous federated learning
  • model heterogeneity
  • data heterogeneity
  • adaptive guidance
  • meta-learning
  • health data
  • 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?

Zhang, J., Liu, Y., Yang, H., Zheng, Z., Yu, H., Zhou, Y., Cao, J., & Yang, Q. (2026). Adaptive Guidance for Local Training in Heterogeneous Federated Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, PP, 1–18. https://doi.org/10.1109/tpami.2026.3748545

How many times has this paper been cited?

3 times, according to OpenAlex on 18 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 Pattern Analysis and Machine Intelligence: sign in and open the full text from this page.

Who wrote this paper?

Jianqing Zhang, Yang Liu, Hua Yang, Zhenzhe Zheng, Han Yu, Yuyin Zhou, Jian Cao, Qiang Yang.

What is the DOI of this paper?

10.1109/tpami.2026.3748545, permanently at https://doi.org/10.1109/tpami.2026.3748545. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.