mlsanityData to 7 Oct 2026

Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning

arXiv 2501.02219 ↗First posted 4 Jan 2025cs.LG cs.AI cs.ITcited by 0

On the map: Diffusion models → Robustness, privacy and adversarial aspects

Abstract (arXiv)

Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we propose a novel approach, diffusion model-based data synthesis aided FSSL (DDSA-FSSL), which utilizes a diffusion model (DM) to generate synthetic data, bridging the gap between heterogeneous local data distributions and the global data distribution. In DDSA-FSSL, clients address the challenge of the scarcity of labeled data by employing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. This process allows clients to generate more comprehensive synthetic datasets aligned with the global distribution. Extensive experiments conducted on multiple datasets and varying non-IID distributions demonstrate the effectiveness of DDSA-FSSL, e.g., it improves accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 15 of its 18 references that are in the map. First posted on arXiv 4 Jan 2025.

Builds on

15 of 18 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model6 May

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,531
  6. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  7. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  8. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 380
  9. 2020Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learningcited by 112
  10. 2023CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communicationscited by 58
  11. 2021Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learningcited by 52
  12. 2021SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labelingcited by 29
2 more
  1. 2022Federated Learning with GAN-based Data Synthesis for Non-IID Clientscited by 25
  2. 2023Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulatorscited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning
  2. 2025Federated Learning for Diffusion Models
  3. 2025FedDifRC: Unlocking the Potential of Text-to-Image Diffusion Models in Heterogeneous Federated Learning
  4. 2024Stable Diffusion-based Data Augmentation for Federated Learning with Non-IID Data
  5. 2023One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
  6. 2025FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models
  7. 2024FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated Diffusion Models
  8. 2024Training Diffusion Models with Federated Learning