Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

CausalFormer: An Interpretable Transformer for Temporal Causal Discovery

About

Temporal causal discovery is a crucial task aimed at uncovering the causal relations within time series data. The latest temporal causal discovery methods usually train deep learning models on prediction tasks to uncover the causality between time series. They capture causal relations by analyzing the parameters of some components of the trained models, e.g., attention weights and convolution weights. However, this is an incomplete mapping process from the model parameters to the causality and fails to investigate the other components, e.g., fully connected layers and activation functions, that are also significant for causal discovery. To facilitate the utilization of the whole deep learning models in temporal causal discovery, we proposed an interpretable transformer-based causal discovery model termed CausalFormer, which consists of the causality-aware transformer and the decomposition-based causality detector. The causality-aware transformer learns the causal representation of time series data using a prediction task with the designed multi-kernel causal convolution which aggregates each input time series along the temporal dimension under the temporal priority constraint. Then, the decomposition-based causality detector interprets the global structure of the trained causality-aware transformer with the proposed regression relevance propagation to identify potential causal relations and finally construct the causal graph. Experiments on synthetic, simulated, and real datasets demonstrate the state-of-the-art performance of CausalFormer on discovering temporal causality. Our code is available at https://github.com/lingbai-kong/CausalFormer.

Lingbai Kong, Wengen Li, Hanchen Yang, Yichao Zhang, Jihong Guan, Shuigeng Zhou• 2024

Related benchmarks

TaskDatasetResultRank
Temporal Causal DiscoveryDataset-1
SHD9
11
Temporal Causal DiscoveryDataset 2
SHD16
11
Temporal Causal DiscoveryArctic Sea Ice
SHD55
11
Temporal Causal DiscoveryTKE
SHD8
11
Temporal Causal DiscoveryfMRI
SHD10
11
Causal DiscoveryfMRI
Structural F166
9
Causal DiscoveryLorenz96
Structural F171
9
Causal DiscoveryV*
Structural F177
9
Causal DiscoveryFork
Structural F179
9
Causal DiscoveryMediator
Structural F171
9
Showing 10 of 17 rows

Other info

Follow for update