Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Jihua, Yao, Yi, Divakaran, Ajay
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2508.15928
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916911907864576
author Huang, Jihua
Yao, Yi
Divakaran, Ajay
author_facet Huang, Jihua
Yao, Yi
Divakaran, Ajay
contents We introduce a novel framework for temporal causal discovery and inference that addresses two key challenges: complex nonlinear dependencies and spurious correlations. Our approach employs a multi-layer Transformer-based time-series forecaster to capture long-range, nonlinear temporal relationships among variables. After training, we extract the underlying causal structure and associated time lags from the forecaster using gradient-based analysis, enabling the construction of a causal graph. To mitigate the impact of spurious causal relationships, we introduce a prior knowledge integration mechanism based on attention masking, which consistently enforces user-excluded causal links across multiple Transformer layers. Extensive experiments show that our method significantly outperforms other state-of-the-art approaches, achieving a 12.8% improvement in F1-score for causal discovery and 98.9% accuracy in estimating causal lags.
format Preprint
id arxiv_https___arxiv_org_abs_2508_15928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transforming Causality: Transformer-Based Temporal Causal Discovery with Prior Knowledge Integration
Huang, Jihua
Yao, Yi
Divakaran, Ajay
Machine Learning
We introduce a novel framework for temporal causal discovery and inference that addresses two key challenges: complex nonlinear dependencies and spurious correlations. Our approach employs a multi-layer Transformer-based time-series forecaster to capture long-range, nonlinear temporal relationships among variables. After training, we extract the underlying causal structure and associated time lags from the forecaster using gradient-based analysis, enabling the construction of a causal graph. To mitigate the impact of spurious causal relationships, we introduce a prior knowledge integration mechanism based on attention masking, which consistently enforces user-excluded causal links across multiple Transformer layers. Extensive experiments show that our method significantly outperforms other state-of-the-art approaches, achieving a 12.8% improvement in F1-score for causal discovery and 98.9% accuracy in estimating causal lags.
title Transforming Causality: Transformer-Based Temporal Causal Discovery with Prior Knowledge Integration
topic Machine Learning
url https://arxiv.org/abs/2508.15928