Federated Adaptation for Foundation Model-Based Recommendations

Abstract

Deep Operator Network (DeepONet) effectively learns complex operator mappings, especially for systems governed by differential equations. Physics-informed DeepONet (PI-DeepONet) extends these capabilities by integrating physical constraints, enabling robust performance with limited or no labeled data. However, combining operator learning with these constraints increases computational complexity, which makes training more difficult and convergence slower, particularly for nonlinear or high-dimensional problems. In this work, we present an enhanced PI-DeepONet framework, that applies importance sampling to both of DeepONet inputs (i.e., the functions and the collocation points) to alleviate these training challenges. By focusing on critical data regions in both input domains, our approach showcases accelerated convergence and improved accuracy across various complex applications.

Cite

Text

Zhang et al. "Federated Adaptation for Foundation Model-Based Recommendations." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/603

Markdown

[Zhang et al. "Federated Adaptation for Foundation Model-Based Recommendations." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/zhang2024ijcai-federated/) doi:10.24963/ijcai.2024/603

BibTeX

@inproceedings{zhang2024ijcai-federated,
  title     = {{Federated Adaptation for Foundation Model-Based Recommendations}},
  author    = {Zhang, Chunxu and Long, Guodong and Guo, Hongkuan and Fang, Xiao and Song, Yang and Liu, Zhaojie and Zhou, Guorui and Zhang, Zijian and Liu, Yang and Yang, Bo},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {5453-5461},
  doi       = {10.24963/ijcai.2024/603},
  url       = {https://mlanthology.org/ijcai/2024/zhang2024ijcai-federated/}
}