Federated Learning from Molecules to Processes: A Perspective

TL;DR

This paper explores federated learning in chemical engineering, demonstrating its ability to improve model accuracy across proprietary datasets without data sharing, through case studies on molecular and process scale applications.

Contribution

It introduces federated learning to chemical engineering, illustrating its practical benefits and potential for collaborative ML development while preserving data privacy.

Findings

Federated learning improves model accuracy over individual training.

Models trained with federated learning perform comparably to combined datasets.

Federated learning enables collaboration without data sharing in chemical industry.

Abstract

We present a perspective on federated learning in chemical engineering that envisions collaborative efforts in machine learning (ML) developments within the chemical industry. Large amounts of chemical and process data are proprietary to chemical companies and are therefore locked in data silos, hindering the training of ML models on large data sets in chemical engineering. Recently, the concept of federated learning has gained increasing attention in ML research, enabling organizations to jointly train machine learning models without disclosure of their individual data. We discuss potential applications of federated learning in several fields of chemical engineering, from the molecular to the process scale. In addition, we apply federated learning in two exemplary case studies that simulate practical scenarios of multiple chemical companies holding proprietary data sets: (i) prediction of binary mixture activity coefficients with graph neural networks and (ii) system identification of a distillation column with autoencoders. Our results indicate that ML models jointly trained with federated learning yield significantly higher accuracy than models trained by each chemical company individually and can perform similarly to models trained on combined datasets from all companies. Federated learning has therefore great potential to advance ML models in chemical engineering while respecting corporate data privacy, making it promising for future industrial applications.