Federated Learning with Heterogeneous and Private Label Sets

• URL: http://arxiv.org/abs/2508.18774v1
• Date: Tue, 26 Aug 2025 07:57:36 GMT
• Title: Federated Learning with Heterogeneous and Private Label Sets
• Authors: Adam Breitholtz, Edvin Listo Zec, Fredrik D. Johansson,
• Abstract summary: heterogeneous client label sets are rarely investigated in federated learning (FL)<n>We study the effects of label set Heterogeneous client label sets on model performance.<n>We show that clients can enjoy increased privacy at little cost to model accuracy.
• Score: 10.355835466049092
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although common in real-world applications, heterogeneous client label sets are rarely investigated in federated learning (FL). Furthermore, in the cases they are, clients are assumed to be willing to share their entire label sets with other clients. Federated learning with private label sets, shared only with the central server, adds further constraints on learning algorithms and is, in general, a more difficult problem to solve. In this work, we study the effects of label set heterogeneity on model performance, comparing the public and private label settings -- when the union of label sets in the federation is known to clients and when it is not. We apply classical methods for the classifier combination problem to FL using centralized tuning, adapt common FL methods to the private label set setting, and discuss the justification of both approaches under practical assumptions. Our experiments show that reducing the number of labels available to each client harms the performance of all methods substantially. Centralized tuning of client models for representational alignment can help remedy this, but often at the cost of higher variance. Throughout, our proposed adaptations of standard FL methods perform well, showing similar performance in the private label setting as the standard methods achieve in the public setting. This shows that clients can enjoy increased privacy at little cost to model accuracy.

Related papers

• Overcoming label shift with target-aware federated learning [10.355835466049092]
  Federated learning enables multiple actors to collaboratively train models without sharing private data.<n>A common reason is label shift -- that the label distributions differ between clients and the target domain.<n>We propose FedPALS, a principled and practical model aggregation scheme that adapts to label shifts to improve performance in the target domain.
  arXiv  Detail & Related papers  (2024-11-06T09:52:45Z)
• (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning [4.803231218533992]
  Federated Learning (FL) is a distributed machine learning framework that trains accurate global models while preserving clients' privacy-sensitive data. Most FL approaches assume that clients possess labeled data, which is often not the case in practice. We propose $(FL)2$, a robust training method for unlabeled clients using sharpness-aware consistency regularization.
  arXiv  Detail & Related papers  (2024-10-30T17:15:02Z)
• Federated Learning with Label-Masking Distillation [33.80340338038264]
  Federated learning provides a privacy-preserving manner to collaboratively train models on data distributed over multiple local clients. Due to the different user behavior of the client, label distributions between different clients are significantly different. We propose a label-masking distillation approach termed FedLMD to facilitate federated learning via perceiving the various label distributions of each client.
  arXiv  Detail & Related papers  (2024-09-20T00:46:04Z)
• Federated Learning with Only Positive Labels by Exploring Label Correlations [78.59613150221597]
  Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting. We propose a novel and generic method termed Federated Averaging by exploring Label Correlations (FedALC)
  arXiv  Detail & Related papers  (2024-04-24T02:22:50Z)
• Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning [55.4510979153023]
  In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth. To help these mislabeled samples "appeal," we propose the first appeal-based framework.
  arXiv  Detail & Related papers  (2023-12-18T09:09:52Z)
• Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data [6.322831694506287]
  Isolated Federated Learning (IsoFed) is a learning scheme specifically designed for semi-supervised federated learning (SSFL) We propose a novel learning scheme specifically designed for SSFL that circumvents the problem by avoiding simple averaging of supervised and semi-supervised models together. In particular, our training approach consists of two parts - (a) isolated aggregation of labeled and unlabeled client models, and (b) local self-supervised pretraining of isolated global models in all clients.
  arXiv  Detail & Related papers  (2023-10-28T20:41:41Z)
• Little is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning [10.972006295280636]
  In many critical applications, sensitive data is inherently distributed and cannot be centralized due to privacy concerns.<n>We propose a federated co-training (FedCT) approach that improves privacy by sharing only definitive (hard) labels on a public unlabeled dataset.
  arXiv  Detail & Related papers  (2023-10-09T13:16:10Z)
• FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels [49.47228898303909]
  Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices. Local training on noisy labels can easily result in overfitting to noisy labels, which is devastating to the global model through aggregation. We develop a simple two-level sampling method "FedNoiL" that selects clients for more robust global aggregation on the server.
  arXiv  Detail & Related papers  (2022-05-20T12:06:39Z)
• On the Convergence of Clustered Federated Learning [57.934295064030636]
  In a federated learning system, the clients, e.g. mobile devices and organization participants, usually have different personal preferences or behavior patterns. This paper proposes a novel weighted client-based clustered FL algorithm to leverage the client's group and each client in a unified optimization framework.
  arXiv  Detail & Related papers  (2022-02-13T02:39:19Z)
• Factorized-FL: Agnostic Personalized Federated Learning with Kernel Factorization & Similarity Matching [70.95184015412798]
  In real-world federated learning scenarios, participants could have their own personalized labels which are incompatible with those from other clients. We introduce Factorized-FL, which allows to effectively tackle label- and task-heterogeneous federated learning settings. We extensively validate our method on both label- and domain-heterogeneous settings, on which it outperforms the state-of-the-art personalized federated learning methods.
  arXiv  Detail & Related papers  (2022-02-01T08:00:59Z)
• Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning [78.88007892742438]
  We study two essential scenarios of Federated Semi-Supervised Learning (FSSL) based on the location of the labeled data. We propose a novel method to tackle the problems, which we refer to as Federated Matching (FedMatch)
  arXiv  Detail & Related papers  (2020-06-22T09:43:41Z)
• Federated Learning with Only Positive Labels [71.63836379169315]
  We propose a generic framework for training with only positive labels, namely Federated Averaging with Spreadout (FedAwS) We show, both theoretically and empirically, that FedAwS can almost match the performance of conventional learning where users have access to negative labels.
  arXiv  Detail & Related papers  (2020-04-21T23:35:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.