データの外の世界を予測する方法を学ぶAI技術 ~ データ駆動型材料研究における有効性を実証 ~

ad

2025-03-03 統計数理研究所

統計数理研究所の研究グループは、学習データの範囲外を予測可能とする機械学習技術「E2T(extrapolative episodic training)」アルゴリズムを開発し、その有効性を材料研究で実証しました。E2Tは、既存データから人工的に多数の外挿的タスクを生成し、メタ学習器を訓練することで、未知の領域における高精度な予測を可能にします。この技術により、学習データに含まれない元素の組み合わせや構造的特徴を持つ材料の特性予測が実現し、新材料の発見やデータ駆動型材料研究の進展が期待されています。

<関連情報>

外挿的エピソード訓練を用いた学習による材料特性の外挿的予測の進展 Advancing extrapolative predictions of material properties through learning to learn using extrapolative episodic training

Kohei Noda,Araki Wakiuchi,Yoshihiro Hayashi & Ryo Yoshida
Communications Materials  Published:22 February 2025
DOI:https://doi.org/10.1038/s43246-025-00754-x

データの外の世界を予測する方法を学ぶAI技術 ~ データ駆動型材料研究における有効性を実証 ~

Abstract

Recent advancements in machine learning have demonstrated its potential to significantly accelerate the discovery of new materials. Central to this progress is the development of rapidly computable property predictors, which allow identifying novel materials with the desired properties from vast material spaces. However, the limited availability of data resources poses a significant challenge in data-driven material research, particularly hindering the exploration of innovative materials beyond the boundaries of existing data. Although machine-learning predictors are inherently interpolative, establishing a general methodology to create an extrapolative predictor remains a fundamental challenge. In this study, we leveraged the attention-based architecture of neural networks and a meta-learning algorithm to enhance extrapolative generalization capabilities. Meta-learners trained repeatedly on arbitrarily generated extrapolative tasks show outstanding generalization for unexplored material spaces. Through the tasks of predicting the physical properties of polymeric materials and hybrid organic–inorganic perovskites, we highlight the potential of such extrapolatively trained models, particularly their ability to rapidly adapt to unseen material domains in transfer-learning scenarios.

1602ソフトウェア工学
ad
ad
Follow
ad
タイトルとURLをコピーしました