CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

Wei Zhang, Thomas K. Panum, Somesh Jha, Prasad Chalasani, David Page

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

19 Downloads (Pure)


We study the problem of learning Granger causality between event types from asynchronous, interdependent, multi-type event sequences. Existing work suffers from either limited model flexibility or poor model explainability and thus fails to uncover Granger causality across a wide variety of event sequences with diverse event interdependency. To address these weaknesses, we propose CAUSE (Causality from AttribUtions on Sequence of Events), a novel framework for the studied task. The key idea of CAUSE is to first implicitly capture the underlying event interdependency by fitting a neural point process, and then extract from the process a Granger causality statistic using an axiomatic attribution method. Across multiple datasets riddled with diverse event interdependency, we demonstrate that CAUSE achieves superior performance on correctly inferring the inter-type Granger causality over a range of state-of-the-art methods.
BogserieThe Proceedings of Machine Learning Research
Sider (fra-til)11235-11245
StatusUdgivet - nov. 2020
BegivenhedInternational Conference on Machine Learning - Virtuel konference
Varighed: 13 jun. 202018 jun. 2020


KonferenceInternational Conference on Machine Learning
LokationVirtuel konference


Dyk ned i forskningsemnerne om 'CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods'. Sammen danner de et unikt fingeraftryk.