Research map / Federated learning and privacy / Personalized and heterogeneous FL
LEGO-FL: Learning Heterogeneous Federated Models as a LEGO Assembly Games
Zeqi Leng, Chunxu Zhang, Guodong Long, Bo Yang
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 |
|---|---|---|---|
| fix the root anchor to the shallowest semantic block (instead of random) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 75.55 -> 79.12 | Improved |
| use ordered-constraint tree search (instead of unconstrained random search) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 73.33 -> 79.12 | Improved |
| add dynamic pool-block completion (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 74.20 -> 79.12 | Improved |
| complete over global unused pool (instead of ordered-constraint scope only) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 71.33 -> 79.12 | Improved |
| use global consensus architecture selection (instead of top-N direct matching) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 72.26 -> 79.12 | Improved |
| use NASWOT zero-cost proxy (instead of Jacov) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 79.00 -> 79.12 | Improved |
| use NASWOT zero-cost proxy (instead of Fisher) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 77.77 -> 79.12 | Improved |
| add personalized grafting (instead of global distillation only) (ablation) | LEGO-FL · CIFAR-10 Non-IID | accuracy (%): 77.16 -> 79.12 | Improved |
| add personalized grafting (instead of global distillation only) (ablation) | LEGO-FL · CIFAR-10 IID | accuracy (%): 78.55 -> 80.60 | Improved |
| use LEGO-FL instead of pFedClub | heterogeneous FL · SVHN Non-IID, Zoo 4 | accuracy (%): 80.55 -> 86.48 | Improved |
| use LEGO-FL instead of FedGH | heterogeneous FL · CIFAR-10 Non-IID, Zoo 4 | accuracy (%): 63.62 -> 79.88 | Improved |
| use LEGO-FL instead of pFedClub with 100 clients | heterogeneous FL · CIFAR-10 Non-IID, N=100 | accuracy (%): 67.74 -> 73.10 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- pfedClub — pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024) · better on 11 of 11 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
- Federated Model Heterogeneous Matryoshka Representation Learning (NeurIPS 2024 · similarity 0.86)
- One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models (ICML 2025 · similarity 0.86)
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.86)
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.85)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.85)
- Federated Learning with Heterogeneous LLMs: Integrating Small Student Client Models with a Large Hungry Model (AAAI 2025 · 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.
