Unknown

Dataset Information

0

Federated learning of molecular properties with graph neural networks in a heterogeneous setting.

ABSTRACT: Chemistry research has both high material and computational costs to conduct experiments. Intuitions are interested in differing classes of molecules, creating heterogeneous data that cannot be easily joined by conventional methods. This work introduces federated heterogeneous molecular learning. Federated learning allows end users to build a global model collaboratively while keeping their training data isolated. We first simulate a heterogeneous federated-learning benchmark (FedChem) by jointly performing scaffold splitting and latent Dirichlet allocation on existing datasets. Our results on FedChem show that significant learning challenges arise when working with heterogeneous molecules across clients. We then propose a method to alleviate the problem: Federated Learning by Instance reweighTing (FLIT(+)). FLIT(+) can align local training across clients. Experiments conducted on FedChem validate the advantages of this method. This work should enable a new type of collaboration for improving artificial intelligence (AI) in chemistry that mitigates concerns about sharing valuable chemical data.

SUBMITTER: Zhu W 

PROVIDER: S-EPMC9214329 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

Federated learning of molecular properties with graph neural networks in a heterogeneous setting.

Zhu Wei W   Luo Jiebo J   White Andrew D AD  

Patterns (New York, N.Y.) 20220602 6

Chemistry research has both high material and computational costs to conduct experiments. Intuitions are interested in differing classes of molecules, creating heterogeneous data that cannot be easily joined by conventional methods. This work introduces federated heterogeneous molecular learning. Federated learning allows end users to build a global model collaboratively while keeping their training data isolated. We first simulate a heterogeneous federated-learning benchmark (FedChem) by jointl  ...[more]

Similar Datasets

Unknown Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning.
| S-EPMC11661272 | biostudies-literature
Unknown Transfer learning with graph neural networks for improved molecular property prediction in the multi-fidelity setting.
| S-EPMC11258334 | biostudies-literature
Unknown Zero-shot learning of aerosol optical properties with graph neural networks.
| S-EPMC10618469 | biostudies-literature
Unknown DGCL: dual-graph neural networks contrastive learning for molecular property prediction.
| S-EPMC11428321 | biostudies-literature
Unknown Learning Cortical Parcellations Using Graph Neural Networks.
| S-EPMC8739886 | biostudies-literature
Unknown Multi-granularity adaptive extractive document summarization with heterogeneous graph neural networks.
| S-EPMC10773739 | biostudies-literature
Unknown Machine Learning Nucleation Collective Variables with Graph Neural Networks.
| S-EPMC10902841 | biostudies-literature
Unknown Generalizable Machine Learning in Neuroscience Using Graph Neural Networks.
| S-EPMC7971515 | biostudies-literature
Unknown Transferable Implicit Solvation via Contrastive Learning of Graph Neural Networks.
| S-EPMC10755853 | biostudies-literature
Unknown Transferable Coarse Graining via Contrastive Learning of Graph Neural Networks.
| S-EPMC10515757 | biostudies-literature