FedBRICK: Structural Bias Aware Heterogeneous Foundation Model Federated Tuning

Yuhang Zhang; Xianda Wang; Wei Sun; Jiaxuan Chen; Fangxin Wang

AAAI 2026technical0 citations

FedBRICK: Structural Bias Aware Heterogeneous Foundation Model Federated Tuning

Yuhang Zhang, Xianda Wang, Wei Sun, Jiaxuan Chen, Fangxin Wang

Abstract

Model-heterogeneous federated tuning (MHFT) enables the privacy-preserving fine-tuning of foundation models in heterogeneous systems by allowing clients and the server to adopt different model architectures. Depth partial training—where each client updates only a subset of the model

BibTeX

@inproceedings{aaai2026_fedbrickstructur,
  title = {FedBRICK: Structural Bias Aware Heterogeneous Foundation Model Federated Tuning},
  author = {Yuhang Zhang and Xianda Wang and Wei Sun and Jiaxuan Chen and Fangxin Wang},
  booktitle = {AAAI 2026},
  year = {2026}
}