Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification

• URL: http://arxiv.org/abs/2603.29633v1
• Date: Tue, 31 Mar 2026 11:59:31 GMT
• Title: Self-Supervised Federated Learning under Data Heterogeneity for Label-Scarce Diatom Classification
• Abstract summary: We introduce self-supervised federated learning (SSFL) for diatom classification as a representative real-world instance.<n>We study cross-site variation in unlabeled data volume during pre-training and label-space misalignment during downstream fine-tuning.<n>Extensive experiments show that SSFL consistently outperforms local-only training under both homogeneous and heterogeneous settings.
• Score: 1.1860671888891074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Label-scarce visual classification under decentralized and heterogeneous data is a fundamental challenge in pattern recognition, especially when sites exhibit partially overlapping class sets. While self-supervised federated learning (SSFL) offers a promising solution, existing studies commonly assume the same data heterogeneity pattern throughout pre-training and fine-tuning. Moreover, current partitioning schemes often fail to generate pure partially class-disjoint data settings, limiting controllable simulation of real-world label-space heterogeneity. In this work, we introduce SSFL for diatom classification as a representative real-world instance and systematically investigate stage-specific data heterogeneity. We study cross-site variation in unlabeled data volume during pre-training and label-space misalignment during downstream fine-tuning. To study the latter in a controllable setting, we propose PreDi, a partitioning scheme that disentangles label-space heterogeneity into two orthogonal dimensions, namely class Prevalence and class-set size Disparity, enabling separate analysis of their effects. Guided by the resulting insights, we further propose PreP-WFL (Prevalence-based Personalized Weighted Federated Learning) to adaptively strengthen rare-class representations in low-prevalence scenarios. Extensive experiments show that SSFL consistently outperforms local-only training under both homogeneous and heterogeneous settings. The pronounced heterogeneity in unlabeled data volume is associated with improved representation pre-training, whereas under label-space heterogeneity, prevalence dominates performance and disparity has a smaller effect. PreP-WFL effectively mitigates this degradation, with gains increasing as prevalence decreases. These findings provide a mechanistic basis for characterizing label-space heterogeneity in decentralized recognition systems.

Related papers

• Closing the Alignment-Maturity Gap in Federated Prototype Learning [42.18063554577504]
  FedSAP is a framework that stabilises federated representation learning through two complementary mechanisms.<n> Experiments show gains of up to 4 percentage points over the prototype-based baselines evaluated.
  arXiv  Detail & Related papers  (2026-06-01T12:30:53Z)
• A Unified Framework for Heterogeneous Semi-supervised Learning [26.87757610311636]
  We introduce a novel problem setup termed Heterogeneous Semi-Supervised Learning (HSSL)<n>HSSL presents unique challenges by bridging the semi-supervised learning (SSL) task and the unsupervised domain adaptation (UDA) task.<n>We propose a novel method, Unified Framework for Heterogeneous Semi-supervised Learning (Uni-HSSL), to address HSSL.
  arXiv  Detail & Related papers  (2025-03-01T01:32:02Z)
• Comparative Evaluation of Clustered Federated Learning Methods [0.5242869847419834]
  Clustered Federated Learning (CFL) aims to partition clients into groups where the distribution are homogeneous. In this paper, we explore the performance of two state-of-theart CFL algorithms with respect to a proposed taxonomy of data heterogeneities in federated learning (FL) Our objective is to provide a clearer understanding of the relationship between CFL performances and data heterogeneous scenarios.
  arXiv  Detail & Related papers  (2024-10-18T07:01:56Z)
• Exploring Vacant Classes in Label-Skewed Federated Learning [113.65301899666645]
  This paper introduces FedVLS, a novel approach to label-skewed federated learning.<n>It integrates vacant-class distillation and logit suppression simultaneously.<n>Experiments validate the efficacy of FedVLS, demonstrating superior performance compared to previous state-of-the-art (SOTA) methods.
  arXiv  Detail & Related papers  (2024-01-04T16:06:31Z)
• Combining propensity score methods with variational autoencoders for generating synthetic data in presence of latent sub-groups [0.0]
  Heterogeneity might be known, e.g., as indicated by sub-groups labels, or might be unknown and reflected only in properties of distributions, such as bimodality or skewness. We investigate how such heterogeneity can be preserved and controlled when obtaining synthetic data from variational autoencoders (VAEs), i.e., a generative deep learning technique.
  arXiv  Detail & Related papers  (2023-12-12T22:49:24Z)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• Generalizable Heterogeneous Federated Cross-Correlation and Instance Similarity Learning [60.058083574671834]
  This paper presents a novel FCCL+, federated correlation and similarity learning with non-target distillation. For heterogeneous issue, we leverage irrelevant unlabeled public data for communication. For catastrophic forgetting in local updating stage, FCCL+ introduces Federated Non Target Distillation.
  arXiv  Detail & Related papers  (2023-09-28T09:32:27Z)
• Rethinking Data Heterogeneity in Federated Learning: Introducing a New Notion and Standard Benchmarks [65.34113135080105]
  We show that not only the issue of data heterogeneity in current setups is not necessarily a problem but also in fact it can be beneficial for the FL participants. Our observations are intuitive. Our code is available at https://github.com/MMorafah/FL-SC-NIID.
  arXiv  Detail & Related papers  (2022-09-30T17:15:19Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)
• Supercharging Imbalanced Data Learning With Energy-based Contrastive Representation Transfer [72.5190560787569]
  In computer vision, learning from long tailed datasets is a recurring theme, especially for natural image datasets. Our proposal posits a meta-distributional scenario, where the data generating mechanism is invariant across the label-conditional feature distributions. This allows us to leverage a causal data inflation procedure to enlarge the representation of minority classes.
  arXiv  Detail & Related papers  (2020-11-25T00:13:11Z)
• Heteroskedastic and Imbalanced Deep Learning with Adaptive Regularization [55.278153228758434]
  Real-world datasets are heteroskedastic and imbalanced. Addressing heteroskedasticity and imbalance simultaneously is under-explored. We propose a data-dependent regularization technique for heteroskedastic datasets.
  arXiv  Detail & Related papers  (2020-06-29T01:09:50Z)
• Fuzziness-based Spatial-Spectral Class Discriminant Information Preserving Active Learning for Hyperspectral Image Classification [0.456877715768796]
  This work proposes a novel fuzziness-based spatial-spectral within and between for both local and global class discriminant information preserving method. Experimental results on benchmark HSI datasets demonstrate the effectiveness of the FLG method on Generative, Extreme Learning Machine and Sparse Multinomial Logistic Regression.
  arXiv  Detail & Related papers  (2020-05-28T18:58:11Z)

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.