Xie, Zikai 
ORCID: 0009-0006-5125-1880, Evangelopoulos, Xenophon, Thacker, Joseph CR and Cooper, Andrew I
(2023)
Domain Knowledge Injection in Bayesian Search for New Materials.
In:
Frontiers in Artificial Intelligence and Applications.
Frontiers in Artificial Intelligence and Applications, 372
.
IOS Press, pp. 2768-2775.
ISBN 9781643684369
Abstract
<jats:p>In this paper we propose DKIBO, a Bayesian optimization (BO) algorithm that accommodates domain knowledge to tune exploration in the search space. Bayesian optimization has recently emerged as a sample-efficient optimizer for many intractable scientific problems. While various existing BO frameworks allow the input of prior beliefs to accelerate the search by narrowing down the space, incorporating such knowledge is not always straightforward and can often introduce bias and lead to poor performance. Here we propose a simple approach to incorporate structural knowledge in the acquisition function by utilizing an additional deterministic surrogate model to enrich the approximation power of the Gaussian process. This is suitably chosen according to structural information of the problem at hand and acts a corrective term towards a better-informed sampling. We empirically demonstrate the practical utility of the proposed method by successfully injecting domain knowledge in a materials design task. We further validate our method’s performance on different experimental settings and ablation analyses.</jats:p>
| Item Type: | Book Section |
|---|---|
| Uncontrolled Keywords: | Generic health relevance |
| Divisions: | Faculty of Science and Engineering > School of Physical Sciences |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 15 Nov 2023 15:46 |
| Last Modified: | 15 Mar 2024 18:36 |
| DOI: | 10.3233/faia230587 |
| Open Access URL: | https://ebooks.iospress.nl/doi/10.3233/FAIA230587 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3176817 |
Dimensions
Dimensions
