nam 22 uu 4500 dbt_mods_00069067 10.1016/j.ifacol.2024.08.304 doi dbt_mods_00069067 ger DE-601 rda eng 2026-01-29 600 sdnb Gao, Xinrui Author aut (DE-588)138438202X Discovering latent causal variables using a trade-off between compression and causality Gao, Xinrui;Huang, Yiman;Shardt, Yuri A.W. (2026-01-29) Frankfurt Elsevier 2024-09-05 6 Seiten text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Causality is a fundamental relationship in the physical world, around which almost all activities of human life revolve. Causal inference refers to the process of determining whether an event or action caused a specific outcome, which involves the evaluation of cause-and-effect relationships in data. This paper presents a new approach to discover latent causal representations of crucial variables in easy-to-obtain data. The proposed method takes a form of trade-off between compression of input data and the causality between the learnt latent variables and critical variables, thereby removing the irrelevant information contained in input data and obtaining the decoupled, strongest causal factors. By introducing variational bounds and specific configurations, the optimisation objective is relaxed to a tractable problem. The approach compacts causal discovery and inference into one model, which is flexible to downstream tasks and parsimonious in the parameters. A case study on an exhaust-emission dataset shows that the proposed method improves the predictive performance over the baseline model, which is a variational information bottleneck model with the same hyperparameters. causal inference information bottleneck latent causal variables soft sensors variational inference article Huang, Yiman Author aut Shardt, Yuri A.W. Author aut (DE-588)1078854556 Technische Universität Ilmenau Fakultät für Informatik und Automatisierung host institution his 12. IFAC Symposium on Advanced Control of Chemical Processes (ADCHEM) (Toronto, 14.-17.07.2024) 58:14<1 Internationale Förderung für Automatische Lenkung; Technische Universität Ilmenau, Universitätsbibliothek IFAC-PapersOnLine 2405-8963 dbt_mods_00048793 Fortsetzung von: Internationale Förderung für Automatische Lenkung: IFAC Proceedings Volumes https://www.db-thueringen.de/receive/dbt_mods_00069067 object in context https://www.db-thueringen.de/servlets/MCRFileNodeServlet/dbt_derivate_00070436/2405-8963_58_2024_14_1-6.pdf raw object https://www.db-thueringen.de/rsc/thumbnail/dbt_mods_00069067.png preview https://www.db-thueringen.de/receive/dbt_mods_00069067 uri