Improving molecular property prediction through a task similarity enhanced transfer learning strategy

HIGHLIGHTS

• who: Han Li from the for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China have published the Article: Improving molecular property prediction through a task similarity enhanced transfer learning strategy, in the Journal: (JOURNAL) of October/21,/2022
• what: The authors propose MoTSE, an interpretable computational framework, to efficiently measure the similarity between molecular property prediction tasks. Based on the task similarity derived from MoTSE, the authors design a novel transfer learning strategy to improve the prediction performance for molecular properties with limited data.
• how: These results indicated that MoTSE can still accurately model . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.