Estimating Before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning
Abstract
Boolean networks (BNs) are widely used to model biological regulatory networks. Attractors here hold significant meaning as they represent long-term behaviors such as homeostasis and the results of cell differentiation. As such, computing attractors is of critical importance to guarantee the validity of a model or to assess its stability and robustness. However, this problem is quite challenging when it comes to large real-world models. To overcome the limits of state-of-the-art BDD-based or ASP-based enumeration approaches, we introduce a SAT-based approach to compute fixed points (singleton attractors) of BN and exhibit its merits for counting the number of singleton attractors of large-scale benchmarks well established in the literature.
Cite
Text
Zhu et al. "Estimating Before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/290Markdown
[Zhu et al. "Estimating Before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/zhu2024ijcai-estimating/) doi:10.24963/ijcai.2024/290BibTeX
@inproceedings{zhu2024ijcai-estimating,
title = {{Estimating Before Debiasing: A Bayesian Approach to Detaching Prior Bias in Federated Semi-Supervised Learning}},
author = {Zhu, Guogang and Liu, Xuefeng and Wu, Xinghao and Tang, Shaojie and Tang, Chao and Niu, Jianwei and Su, Hao},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {2625-2633},
doi = {10.24963/ijcai.2024/290},
url = {https://mlanthology.org/ijcai/2024/zhu2024ijcai-estimating/}
}