mlsanityData to 7 Oct 2026

FedPhD: Federated Pruning with Hierarchical Learning of Diffusion Models

arXiv 2507.06449 ↗First posted 8 Jul 2025cs.LG cs.AI cs.DCcited by 1

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

Abstract (arXiv)

Federated Learning (FL), as a distributed learning paradigm, trains models over distributed clients' data. FL is particularly beneficial for distributed training of Diffusion Models (DMs), which are high-quality image generators that require diverse data. However, challenges such as high communication costs and data heterogeneity persist in training DMs similar to training Transformers and Convolutional Neural Networks. Limited research has addressed these issues in FL environments. To address this gap and challenges, we introduce a novel approach, FedPhD, designed to efficiently train DMs in FL environments. FedPhD leverages Hierarchical FL with homogeneity-aware model aggregation and selection policy to tackle data heterogeneity while reducing communication costs. The distributed structured pruning of FedPhD enhances computational efficiency and reduces model storage requirements in clients. Our experiments across multiple datasets demonstrate that FedPhD achieves high model performance regarding Fr'echet Inception Distance (FID) scores while reducing communication costs by up to 88%. FedPhD outperforms baseline methods achieving at least a 34% improvement in FID, while utilizing only 56% of the total computation and communication resources.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models. Builds on 25 of its 34 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

25 of 34 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Training Diffusion Models with Federated Learning18 Jun
  2. 2023Federated Learning with Diffusion Models for Privacy-Sensitive Vision Tasks28 Nov
  3. 2023Phoenix: A Federated Generative Diffusion Model7 Jun
  4. 2023Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model6 May

Other references · 21

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  7. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  8. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  9. 2018Federated Learning with Non-IID Datacited by 1,099
  10. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  11. 2021Model-Contrastive Federated Learningcited by 762
  12. 2022Post-training Quantization on Diffusion Modelscited by 262
9 more
  1. 2023DepGraph: Towards Any Structural Pruningcited by 202
  2. 2023Structural Pruning for Diffusion Modelscited by 193
  3. 2021DENSE: Data-Free One-Shot Federated Learningcited by 100
  4. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  5. 2023When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directionscited by 83
  6. 2023Knowledge Diffusion for Distillationcited by 51
  7. 2023Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Modelscited by 49
  8. 2023FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clientscited by 23
  9. 2022Mitigating Data Heterogeneity in Federated Learning with Data Augmentationcited by 21

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cooperative Perception: A Resource-Efficient Framework for Multi-Drone 3D Scene Reconstruction Using Federated Diffusion and NeRFcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Federated Learning for Diffusion Models
  2. 2024FedDM: Enhancing Communication Efficiency and Handling Data Heterogeneity in Federated 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. 2024FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models
  6. 2025Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning
  7. 2023One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models
  8. 2022FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers