Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedBRICK: Structural Bias Aware Heterogeneous Foundation Model Federated Tuning
Yuhang Zhang, Xianda Wang, Wei Sun, Jiaxuan Chen, Fangxin Wang
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 BRICK modules in place of missing layers to FedRA | FedRA · DomainNet average (uneven layers), ViT | accuracy (%): 65.31 -> 70.33 | Improved |
| add BRICK modules to FedRA | FedRA · DomainNet average (uneven layers), Mixer | accuracy (%): 52.71 -> 56.28 | Improved |
| add BRICK modules to FedRA | FedRA · NICO++ average (uneven layers), ViT | accuracy (%): 86.79 -> 88.11 | Improved |
| add BRICK modules to FedRA on quickdraw domain with 6 layers | FedRA · DomainNet quickdraw (6 layers), ViT | accuracy (%): 26.94 -> 46.98 | Improved |
| add BRICK modules when every client keeps only 4 layers | FedRA · DomainNet average (all clients 4 layers), ViT | accuracy (%): 14.90 -> 43.86 | Improved |
| add BRICK modules when every client keeps only 4 layers | FedRA · DomainNet average (all clients 4 layers), Mixer | accuracy (%): 14.52 -> 17.18 | Improved |
| add BRICK modules when every client keeps 6 layers | FedRA · DomainNet average (all clients 6 layers), ViT | accuracy (%): 53.45 -> 65.77 | Improved |
| plug BRICK into DepthFL and InclusiveFL as well | DepthFL, InclusiveFL, FedRA · DomainNet and NICO++ (ViT) | accuracy (%) | Improved |
| add BRICK modules to FedRA | FedRA · DomainNet client representations | cosine distance across clients | Improved |
| gain from BRICK is larger on clients with fewer layers | FedBRICK · DomainNet and NICO++ | accuracy (%): +12.32 (6 layers) vs +28.97 (4 layers), ViT | Improved |
| add BRICK to Mixer when all clients have 4 layers (clipart) | FedRA · DomainNet clipart (4 layers), Mixer | accuracy (%): 20.33 -> 20.50 | No clear effect |
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.
- FedRA — FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients (ECCV 2024) · better on 9 of 9 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
- Cluster Based Heterogeneous Federated Foundation Model Adaptation and Fine-Tuning (AAAI 2025 · similarity 0.88)
- Watch Your Head: Assembling Projection Heads to Save the Reliability of Federated Models (AAAI 2024 · similarity 0.87)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.87)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.87)
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 2024 · similarity 0.86)
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning (AAAI 2024 · similarity 0.86)
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.
