Multi-modal cascade feature transfer for polymer property prediction

Kiichi Obuchi, Yuta Yahagi, Kota Matsui, Kiyohiko Toyama, Shukichi Tanaka

Submission Track: Short Paper

Submission Category: AI-Guided Design

Keywords: transfer learning, polymer, feature transfer, cascade

TL;DR: This paper proposes a multi-modal cascade model with feature transfer for polymer property prediction, achieving superior accuracy with only 20 training data points, compared to the benchmark's 110.

Abstract:

In this paper, we put forth a multi-modal cascade model with feature transfer with the aim of adjusting the characteristics of polymer property prediction. Polymers are characterised by a composite of data in several different formats, including molecular descriptors and additive information as well as chemical structures. Our model enables more accurate prediction of physical properties for polymers by combining features extracted from the chemical structure by GCN with features such as molecular descriptors and additive information. The predictive performance of the proposed method is empirically evaluated using several polymer datasets.
We report that the proposed method shows high predictive performance compared to the baseline conventional approach using a single feature.

AI4Mat Journal Track: Yes

Submission Number: 29