Feature Norm Regularized Federated Learning: Utilizing Data Disparities for Model Performance Gains
Abstract
In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a mechanism humans rely on to implicitly align with teammates. To address this gap, we introduce HA^2: Hierarchical Ad Hoc Agents, a framework leveraging hierarchical reinforcement learning to mimic the structured approach humans use in collaboration. We evaluate HA^2 in the Overcooked environment, demonstrating statistically significant improvement over existing baselines when paired with both unseen agents and humans, providing better resilience to environmental shifts, and outperforming all state-of-the-art methods.
Cite
Text
Hu et al. "Feature Norm Regularized Federated Learning: Utilizing Data Disparities for Model Performance Gains." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/457Markdown
[Hu et al. "Feature Norm Regularized Federated Learning: Utilizing Data Disparities for Model Performance Gains." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/hu2024ijcai-feature/) doi:10.24963/ijcai.2024/457BibTeX
@inproceedings{hu2024ijcai-feature,
title = {{Feature Norm Regularized Federated Learning: Utilizing Data Disparities for Model Performance Gains}},
author = {Hu, Ke and Xiang, Liyao and Tang, Peng and Qiu, Weidong},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {4136-4146},
doi = {10.24963/ijcai.2024/457},
url = {https://mlanthology.org/ijcai/2024/hu2024ijcai-feature/}
}