Skip to main content
Springer Nature Link
Log in

Federated Learning with Local Openset Noisy Labels

  • Conference paper
  • First Online:
Computer Vision – ECCV 2024 (ECCV 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 15092))

Included in the following conference series:

Abstract

Federated learning (FL) is a learning paradigm that allows the central server to learn from different data sources while keeping the data private locally. Without controlling and monitoring the local data collection process, the locally available training labels are likely noisy, i.e., the collected training labels differ from the unobservable ground truth. Additionally, in heterogenous FL, each local client may only have access to a subset of label space (referred to as openset label learning), meanwhile without overlapping with others. In this work, we study the challenge of FL with local openset noisy labels. We observe that many existing solutions in the noisy label literature, e.g., loss correction, are ineffective during local training due to overfitting to noisy labels and being not generalizable to openset labels. For the methods in FL, different estimated metrics are shared. To address the problems, we design a label communication mechanism that shares “contrastive labels” randomly selected from clients with the server. The privacy of the shared contrastive labels is protected by label differential privacy (DP). Both the DP guarantee and the effectiveness of our approach are theoretically guaranteed. Compared with several baseline methods, our solution shows its efficiency in several public benchmarks and real-world datasets under different noise ratios and noise models. Our code is publicly available at https://github.com/UCSC-REAL/FedDPCont.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Noise ratio is the ratio of the corrupted (wrong) labels in the local dataset.

References

  1. Acar, D.A.E., Zhao, Y., Navarro, R.M., Mattina, M., Whatmough, P.N., Saligrama, V.: Federated learning based on dynamic regularization. arXiv preprint arXiv:2111.04263 (2021)

  2. Agarwal, V., et al.: Learning statistical models of phenotypes using noisy labeled training data. J. Am. Med. Inform. Assoc. 23(6), 1166–1173 (2016)

    Article  Google Scholar 

  3. Andreux, M., du Terrail, J.O., Beguier, C., Tramel, E.W.: Siloed federated learning for multi-centric histopathology datasets. In: Albarqouni, S., et al. (eds.) DART/DCL -2020. LNCS, vol. 12444, pp. 129–139. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60548-3_13

    Chapter  Google Scholar 

  4. Aono, Y., Hayashi, T., Wang, L., Moriai, S., et al.: Privacy-preserving deep learning via additively homomorphic encryption. IEEE Trans. Inf. Forensics Secur. 13(5), 1333–1345 (2017)

    Google Scholar 

  5. Bae, H., Shin, S., Na, B., Jang, J., Song, K., Moon, I.C.: From noisy prediction to true label: Noisy prediction calibration via generative model. In: International Conference on Machine Learning, pp. 1277–1297. PMLR (2022)

    Google Scholar 

  6. Chen, D., Gao, D., Kuang, W., Li, Y., Ding, B.: pfl-bench: a comprehensive benchmark for personalized federated learning. Adv. Neural. Inf. Process. Syst. 35, 9344–9360 (2022)

    Google Scholar 

  7. Cheng, H., Zhu, Z., Li, X., Gong, Y., Sun, X., Liu, Y.: Learning with instance-dependent label noise: a sample sieve approach. arXiv preprint arXiv:2010.02347 (2020)

  8. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)

    Google Scholar 

  9. Fang, X., Ye, M.: Robust federated learning with noisy and heterogeneous clients. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10072–10081 (2022)

    Google Scholar 

  10. Feng, L., Shu, S., Lin, Z., Lv, F., Li, L., An, B.: Can cross entropy loss be robust to label noise? In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, pp. 2206–2212 (2021)

    Google Scholar 

  11. Geiping, J., Bauermeister, H., Dröge, H., Moeller, M.: Inverting gradients-how easy is it to break privacy in federated learning? Adv. Neural. Inf. Process. Syst. 33, 16937–16947 (2020)

    Google Scholar 

  12. Geng, C., Huang, S.j., Chen, S.: Recent advances in open set recognition: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3614–3631 (2020)

    Google Scholar 

  13. Ghazi, B., Golowich, N., Kumar, R., Manurangsi, P., Zhang, C.: Deep learning with label differential privacy. Adv. Neural. Inf. Process. Syst. 34, 27131–27145 (2021)

    Google Scholar 

  14. Ghosh, A., Kumar, H., Sastry, P.S.: Robust loss functions under label noise for deep neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 31 (2017)

    Google Scholar 

  15. Han, B., et al.: A survey of label-noise representation learning: past, present and future. arXiv preprint arXiv:2011.04406 (2020)

  16. Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. Advances in neural information processing systems 31 (2018)

    Google Scholar 

  17. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)

    Google Scholar 

  18. Ji, X., et al.: Fedfixer: mitigating heterogeneous label noise in federated learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 12830–12838 (2024)

    Google Scholar 

  19. Jiang, Z., et al.: An information fusion approach to learning with instance-dependent label noise. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=ecH2FKaARUp

  20. Karimireddy, S.P., Kale, S., Mohri, M., Reddi, S., Stich, S., Suresh, A.T.: Scaffold: stochastic controlled averaging for federated learning. In: International Conference on Machine Learning, pp. 5132–5143. PMLR (2020)

    Google Scholar 

  21. Kim, S., Shin, W., Jang, S., Song, H., Yun, S.Y.: Fedrn: exploiting k-reliable neighbors towards robust federated learning. In: Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pp. 972–981 (2022)

    Google Scholar 

  22. Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)

    Google Scholar 

  23. Li, J., Socher, R., Hoi, S.C.: Dividemix: learning with noisy labels as semi-supervised learning. In: International Conference on Learning Representations (2020). https://openreview.net/forum?id=HJgExaVtwr

  24. Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks. Proc. Mach. Learn. Syst. 2, 429–450 (2020)

    Google Scholar 

  25. Li, X., Huang, K., Yang, W., Wang, S., Zhang, Z.: On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189 (2019)

  26. Li, X., Jiang, M., Zhang, X., Kamp, M., Dou, Q.: Fedbn: federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623 (2021)

  27. Liu, S., Niles-Weed, J., Razavian, N., Fernandez-Granda, C.: Early-learning regularization prevents memorization of noisy labels. Adv. Neural. Inf. Process. Syst. 33, 20331–20342 (2020)

    Google Scholar 

  28. Liu, T., Tao, D.: Classification with noisy labels by importance reweighting. IEEE Trans. Pattern Anal. Mach. Intell. 38(3), 447–461 (2015)

    Article  Google Scholar 

  29. Liu, Y.: Understanding instance-level label noise: disparate impacts and treatments. In: International Conference on Machine Learning, pp. 6725–6735. PMLR (2021)

    Google Scholar 

  30. Liu, Y., Guo, H.: Peer loss functions: learning from noisy labels without knowing noise rates. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020 (2020)

    Google Scholar 

  31. Liu, Y., Wang, J.: Can less be more? when increasing-to-balancing label noise rates considered beneficial. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 17467–17479. Curran Associates, Inc. (2021). https://proceedings.neurips.cc/paper/2021/file/91e50fe1e39af2869d3336eaaeebdb43-Paper.pdf

  32. McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, pp. 1273–1282. PMLR (2017)

    Google Scholar 

  33. Melis, L., Song, C., De Cristofaro, E., Shmatikov, V.: Exploiting unintended feature leakage in collaborative learning. In: 2019 IEEE Symposium on Security and Privacy (SP), pp. 691–706. IEEE (2019)

    Google Scholar 

  34. Menon, A., Van Rooyen, B., Ong, C.S., Williamson, B.: Learning from corrupted binary labels via class-probability estimation. In: International Conference on Machine Learning, pp. 125–134 (2015)

    Google Scholar 

  35. Natarajan, N., Dhillon, I.S., Ravikumar, P.K., Tewari, A.: Learning with noisy labels. In: Advances in neural information processing systems, pp. 1196–1204 (2013)

    Google Scholar 

  36. Pan, X., Zhang, M., Ji, S., Yang, M.: Privacy risks of general-purpose language models. In: 2020 IEEE Symposium on Security and Privacy (SP), pp. 1314–1331. IEEE (2020)

    Google Scholar 

  37. Patrini, G., Rozza, A., Krishna Menon, A., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1944–1952 (2017)

    Google Scholar 

  38. Qin, Z., Yao, L., Chen, D., Li, Y., Ding, B., Cheng, M.: Revisiting personalized federated learning: Robustness against backdoor attacks. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4743–4755 (2023)

    Google Scholar 

  39. Scott, C.: A rate of convergence for mixture proportion estimation, with application to learning from noisy labels. In: AISTATS (2015)

    Google Scholar 

  40. Shokri, R., Shmatikov, V.: Privacy-preserving deep learning. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, pp. 1310–1321 (2015)

    Google Scholar 

  41. Song, H., Kim, M., Park, D., Lee, J.G.: How does early stopping help generalization against label noise? arXiv preprint arXiv:1911.08059 (2019)

  42. Wang, J., Liu, Y., Levy, C.: Fair classification with group-dependent label noise. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2021, pp. 526–536. Association for Computing Machinery, New York (2021). https://doi.org/10.1145/3442188.3445915

  43. Tuor, T., Wang, S., Ko, B.J., Liu, C., Leung, K.K.: Overcoming noisy and irrelevant data in federated learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 5020–5027. IEEE (2021)

    Google Scholar 

  44. Vaze, S., Han, K., Vedaldi, A., Zisserman, A.: Open-set recognition: a good closed-set classifier is all you need? arXiv preprint arXiv:2110.06207 (2021)

  45. Wei, J., Liu, H., Liu, T., Niu, G., Liu, Y.: To smooth or not? when label smoothing meets noisy labels. In: ICML (2022)

    Google Scholar 

  46. Wei, J., Liu, Y.: When optimizing \$f\$-divergence is robust with label noise. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=WesiCoRVQ15

  47. Wei, J., Zhu, Z., Cheng, H., Liu, T., Niu, G., Liu, Y.: Learning with noisy labels revisited: a study using real-world human annotations. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=TBWA6PLJZQm

  48. Wei, J., Zhu, Z., Luo, T., Amid, E., Kumar, A., Liu, Y.: To aggregate or not? learning with separate noisy labels. In: ACM SIGKDD Conference on Knowledge Discovery and Data Mining (2023)

    Google Scholar 

  49. Wu, N., Yu, L., Jiang, X., Cheng, K.T., Yan, Z.: Fednoro: towards noise-robust federated learning by addressing class imbalance and label noise heterogeneity. arXiv preprint arXiv:2305.05230 (2023)

  50. Xia, X., Liu, T., Han, B., Gong, C., Wang, N., Ge, Z., Chang, Y.: Robust early-learning: hindering the memorization of noisy labels. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=Eql5b1_hTE4

  51. Xia, X., Liu, T., Wang, N., Han, B., Gong, C., Niu, G., Sugiyama, M.: Are anchor points really indispensable in label-noise learning? Advances in Neural Information Processing Systems 32 (2019)

    Google Scholar 

  52. Xiao, T., Xia, T., Yang, Y., Huang, C., Wang, X.: Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2691–2699 (2015)

    Google Scholar 

  53. Xu, J., Chen, Z., Quek, T.Q., Chong, K.F.E.: Fedcorr: multi-stage federated learning for label noise correction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10184–10193 (2022)

    Google Scholar 

  54. Yang, S., Park, H., Byun, J., Kim, C.: Robust federated learning with noisy labels. IEEE Intell. Syst. 37(2), 35–43 (2022)

    Article  Google Scholar 

  55. Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. In: International Conference on Learning Representations (2018). https://openreview.net/forum?id=r1Ddp1-Rb

  56. Zhang, J., Sheng, V.S., Li, T., Wu, X.: Improving crowdsourced label quality using noise correction. IEEE Trans. Neural Networks Learn. Syst. 29(5), 1675–1688 (2017)

    Article  MathSciNet  Google Scholar 

  57. Zhang, L., Luo, Y., Bai, Y., Du, B., Duan, L.Y.: Federated learning for non-iid data via unified feature learning and optimization objective alignment. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4420–4428 (2021)

    Google Scholar 

  58. Zhang, Y., Niu, G., Sugiyama, M.: Learning noise transition matrix from only noisy labels via total variation regularization. arXiv preprint arXiv:2102.02414 (2021)

  59. Zhang, Z., Sabuncu, M.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: Advances in neural information processing systems, pp. 8778–8788 (2018)

    Google Scholar 

  60. Zhao, B., Mopuri, K.R., Bilen, H.: idlg: improved deep leakage from gradients. arXiv preprint arXiv:2001.02610 (2020)

  61. Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with non-iid data. arXiv preprint arXiv:1806.00582 (2018)

  62. Zhu, Z., Liu, T., Liu, Y.: A second-order approach to learning with instance-dependent label noise. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10113–10123 (2021)

    Google Scholar 

  63. Zhu, Z., Song, Y., Liu, Y.: Clusterability as an alternative to anchor points when learning with noisy labels. In: International Conference on Machine Learning, pp. 12912–12923. PMLR (2021)

    Google Scholar 

  64. Zhu, Z., Wang, J., Cheng, H., Liu, Y.: Unmasking and improving data credibility: a study with datasets for training harmless language models. arXiv preprint arXiv:2311.11202 (2023)

  65. Zhu, Z., Wang, J., Cheng, H., Liu, Y.: Unmasking and improving data credibility: a study with datasets for training harmless language models. In: The Twelfth International Conference on Learning Representations (2024). https://openreview.net/forum?id=6bcAD6g688

  66. Zhu, Z., Wang, J., Liu, Y.: Beyond images: label noise transition matrix estimation for tasks with lower-quality features. arXiv preprint arXiv:2202.01273 (2022)

Download references

Acknowledgements

Z. Di and Y. Liu are partially supported by the National Science Foundation (NSF) under grants IIS-2007951 and IIS-2143895. X. Li is supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC).

Author information

Authors and Affiliations

  1. University of California, Santa Cruz, Santa Cruz, CA, 95064, USA

    Zonglin Di & Yang Liu

  2. Docta.ai, San Jose, CA, 95112, USA

    Zhaowei Zhu

  3. University of British Columbia, Vancouver, BC, V6T 1Z4, Canada

    Xiaoxiao Li

  4. Vector Institute, Toronto, ON, M5G 1M1, Canada

    Xiaoxiao Li

Authors
  1. Zonglin Di
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhaowei Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaoxiao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zonglin Di .

Editor information

Editors and Affiliations

  1. University of Birmingham, Birmingham, UK

    Aleš Leonardis

  2. University of Trento, Trento, Italy

    Elisa Ricci

  3. Technical University of Darmstadt, Darmstadt, Germany

    Stefan Roth

  4. Princeton University, Princeton, NJ, USA

    Olga Russakovsky

  5. Czech Technical University in Prague, Prague, Czech Republic

    Torsten Sattler

  6. École des Ponts ParisTech, Marne-la-Vallée, France

    Gül Varol

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 1179410 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Di, Z., Zhu, Z., Li, X., Liu, Y. (2025). Federated Learning with Local Openset Noisy Labels. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15092. Springer, Cham. https://doi.org/10.1007/978-3-031-72754-2_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-72754-2_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-72753-5

  • Online ISBN: 978-3-031-72754-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics