Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining
This work addresses the challenge of cross-task generalization in time-series causal discovery, which is critical for applications like root cause analysis, by enabling transferable causal learning.
PTCD introduces a pretraining framework for time-series causal discovery that uses context-conditioned modeling and causal augmentation to generalize across diverse causal mechanisms, achieving superior performance on multiple real-world OOD datasets for both causal discovery and root cause identification.
Causal discovery from time series is critical for many real-world applications, such as tracing the root causes of anomalies. Existing approaches typically rely on dataset-specific optimization, making it difficult to transfer their causal discovery capabilities to new time series governed by diverse causal mechanisms. In this paper, we propose \textbf{PTCD}, a novel \textbf{P}retraining framework for \textbf{T}ime-series \textbf{C}ausal \textbf{D}iscovery, which improves cross-task generalization through context-conditioned modeling and transferable causal augmentation. To model complex temporal causal dependencies, PTCD employs a dual-scale iterative attention mechanism to capture window-level causal relationships, and a Gaussian mixture with a context-level routing mechanism to handle heterogeneous exogenous distributions. To further address distribution shifts across causal graphs, PTCD adopts a pretraining paradigm on synthetic datasets that integrates intervention-based learning and a causal mixup strategy, promoting stable causal discovery and stronger generalization. Extensive experiments on multiple real-world out-of-distribution (OOD) datasets demonstrate that PTCD excels in both causal discovery and root cause identification.