Prospects of Continual Causality for Industrial Applications

Daigo Fujiwara, Kazuki Koyama, Keisuke Kiritoshi, Tomomi Okawachi, Tomonori Izumitani, Shohei Shimizu

Keywords: Causality, Continual Learning, Causal Discovery, Industrial Plants, Process Data, Time-series, Just-In-Time Modeling

TL;DR: This paper shows the challenges and prospects for industrial applications of causality accelerated by continual learning. We also introduce briefly the new specific causal discovery method combining continual learning and causality.

Abstract: We have been investigating the causal analysis of industrial plant process data and its various applications, such as material quantity optimization utilizing intervention effects. However, process data often comes with various problems such as non-stationary characteristics including distribution shifts, which make such applications difficult. When combined with the idea of continual learning, causal models may be able to solve these problems. We present the potential and prospects for industrial applications of continual causality, showing previous work. We also briefly introduce our causal discovery method utilizing a continual framework.