Scalable Multi-Task Transfer Learning for Molecular Property Prediction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914961389780992 |
|---|---|
| author | Lee, Chanhui Jeong, Dae-Woong Ko, Sung Moon Lee, Sumin Kim, Hyunseung Yim, Soorin Han, Sehui Kim, Sungwoong Lim, Sungbin |
| author_facet | Lee, Chanhui Jeong, Dae-Woong Ko, Sung Moon Lee, Sumin Kim, Hyunseung Yim, Soorin Han, Sehui Kim, Sungwoong Lim, Sungbin |
| contents | Molecules have a number of distinct properties whose importance and application vary. Often, in reality, labels for some properties are hard to achieve despite their practical importance. A common solution to such data scarcity is to use models of good generalization with transfer learning. This involves domain experts for designing source and target tasks whose features are shared. However, this approach has limitations: i). Difficulty in accurate design of source-target task pairs due to the large number of tasks, and ii). corresponding computational burden verifying many trials and errors of transfer learning design, thereby iii). constraining the potential of foundation modeling of multi-task molecular property prediction. We address the limitations of the manual design of transfer learning via data-driven bi-level optimization. The proposed method enables scalable multi-task transfer learning for molecular property prediction by automatically obtaining the optimal transfer ratios. Empirically, the proposed method improved the prediction performance of 40 molecular properties and accelerated training convergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00432 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Scalable Multi-Task Transfer Learning for Molecular Property Prediction Lee, Chanhui Jeong, Dae-Woong Ko, Sung Moon Lee, Sumin Kim, Hyunseung Yim, Soorin Han, Sehui Kim, Sungwoong Lim, Sungbin Machine Learning Artificial Intelligence Molecules have a number of distinct properties whose importance and application vary. Often, in reality, labels for some properties are hard to achieve despite their practical importance. A common solution to such data scarcity is to use models of good generalization with transfer learning. This involves domain experts for designing source and target tasks whose features are shared. However, this approach has limitations: i). Difficulty in accurate design of source-target task pairs due to the large number of tasks, and ii). corresponding computational burden verifying many trials and errors of transfer learning design, thereby iii). constraining the potential of foundation modeling of multi-task molecular property prediction. We address the limitations of the manual design of transfer learning via data-driven bi-level optimization. The proposed method enables scalable multi-task transfer learning for molecular property prediction by automatically obtaining the optimal transfer ratios. Empirically, the proposed method improved the prediction performance of 40 molecular properties and accelerated training convergence. |
| title | Scalable Multi-Task Transfer Learning for Molecular Property Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.00432 |