Research map / Federated learning and privacy / Personalized and heterogeneous FL
Neural Architecture Search Driven by Locally Guided Diffusion for Personalized Federated Learning
Peng Liao, Xilu Wang, Yaochu Jin, Wenli Du, Han Hu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add conditional diffusion architecture generation (ablation) | PerFedSDE-NAS · CIFAR-100 (alpha=0.1) MobileNetV3 | accuracy: 62.29 -> 64.15 | Improved |
| add conditional diffusion architecture generation (ablation) | PerFedSDE-NAS · CIFAR-10 (alpha=0.3) MobileNetV3 | accuracy: 80.59 -> 82.62 | Improved |
| add archive-based supernet training (ablation) | PerFedSDE-NAS · CIFAR-10 (alpha=0.3) MobileNetV3 | accuracy: 81.82 -> 82.62 | Improved |
| add archive-based supernet training (ablation) | PerFedSDE-NAS · CIFAR-100 (alpha=0.1) MobileNetV3 | accuracy: 62.27 -> 64.15 | Improved |
| add Eq. 5 supernet aggregation (ablation) | PerFedSDE-NAS · CIFAR-10 (alpha=0.3) MobileNetV3 | accuracy: 80.01 -> 82.62 | Improved |
| add Eq. 5 supernet aggregation (ablation) | PerFedSDE-NAS · CIFAR-100 (alpha=0.1) MobileNetV3 | accuracy: 62.74 -> 64.15 | Improved |
| add all three components (ablation) | PerFedSDE-NAS · CIFAR-100 (alpha=0.1) MobileNetV3 | accuracy: 58.89 -> 64.15 | Improved |
| diffusion generation vs crossover and mutation | client-side NAS · CIFAR-10 (alpha=0.3) DARTS | accuracy: 79.99 -> 81.65 | Improved |
| diffusion generation vs crossover and mutation | client-side NAS · CIFAR-100 (alpha=0.1) NASViT | accuracy: 62.89 -> 65.94 | Improved |
| client-side PerFedSDE-NAS vs server-side PerFedRLNAS | personalized FL · CIFAR-100 (alpha=0.1) MobileNetV3 | accuracy: 63.85 -> 64.15 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PerFedRLNAS — PerFedRLNAS: One-for-All Personalized Federated Neural Architecture Search (AAAI 2024) · better on 6 of 6 shared results
- FedBABU — FedBABU: Toward Enhanced Representation for Federated Image Classification (ICLR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Large Language Models Enhanced Personalized Graph Neural Architecture Search in Federated Learning (AAAI 2025 · similarity 0.89)
- PerFedRLNAS: One-for-All Personalized Federated Neural Architecture Search (AAAI 2024 · similarity 0.89)
- Rethinking Architecture Selection in Differentiable NAS (ICLR 2021 · similarity 0.86)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.86)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 2024 · similarity 0.85)
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
