Fast and effective molecular property prediction with transferability map
Abstract Effective transfer learning for molecular property prediction has shown considerable strength in addressing insufficient labeled molecules. Many existing methods either disregard the quantitative relationship between source and target properties, risking negative transfer, or require intens...
Main Authors: | Shaolun Yao, Jie Song, Lingxiang Jia, Lechao Cheng, Zipeng Zhong, Mingli Song, Zunlei Feng |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2024-04-01
|
Series: | Communications Chemistry |
Online Access: | https://doi.org/10.1038/s42004-024-01169-4 |
Similar Items
-
Explainable Fragment‐Based Molecular Property Attribution
by: Lingxiang Jia, et al.
Published: (2022-10-01) -
Federated selective aggregation for on-device knowledge amalgamation
by: Donglin Xie, et al.
Published: (2023-09-01) -
A Fast Image Segmentation Algorithm Based on Saliency Map and Neutrosophic Set Theory
by: Sensen Song, et al.
Published: (2020-01-01) -
Prediction of Molecular Properties Using Molecular Topographic Map
by: Atsushi Yoshimori
Published: (2021-07-01) -
Finite Time Trajectory Tracking with Full-State Feedback of Underactuated Unmanned Surface Vessel Based on Nonsingular Fast Terminal Sliding Mode
by: Donghao Xu, et al.
Published: (2022-12-01)