Scholarlink

This paper introduces the Causal Temporal Transformer (CTT), an end-to-end trainable transformer-based model designed for the dual tasks of causal time-series discovery and multi-target prediction. At its core, CTT employs a causal attention mechanism to distinguish and emphasize causal components while suppressing non-causal ones, thereby improving interpretability and feature relevance. Furthermore, to capture temporal dependencies with greater precision, the Lag Temporal (LT) embedding is incorporated, which facilitates the analysis of lagging characteristics intrinsic to the data. Notably, CTT can generate a causal graph that elucidates the potential causal relationships among the targeted variables and the prediction sequence, thereby enriching the interpretability of the model’s outputs. Experiments on Netsim, Kuramoto, and Lorenz-96 benchmarks demonstrate CTT’s superior causal time-series discovery capabilities, outperforming recent methods. Evaluations on ETH-UCY, nuScenes, and TrajAir datasets further show significant gains in multi-target prediction accuracy over baselines. Overall, CTT offers a robust, interpretable framework aligning inferred causal attributions with underlying drivers of multi-target time-series data.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Causal Temporal Transformer: An Integrated Framework for Temporal Causal Discovery and Multi-target Prediction

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Quang Le,
  • Sepideh Mousazadeh,
  • Francois Chan,
  • Claude D’Amours,
  • Il-Min Kim

摘要

This paper introduces the Causal Temporal Transformer (CTT), an end-to-end trainable transformer-based model designed for the dual tasks of causal time-series discovery and multi-target prediction. At its core, CTT employs a causal attention mechanism to distinguish and emphasize causal components while suppressing non-causal ones, thereby improving interpretability and feature relevance. Furthermore, to capture temporal dependencies with greater precision, the Lag Temporal (LT) embedding is incorporated, which facilitates the analysis of lagging characteristics intrinsic to the data. Notably, CTT can generate a causal graph that elucidates the potential causal relationships among the targeted variables and the prediction sequence, thereby enriching the interpretability of the model’s outputs. Experiments on Netsim, Kuramoto, and Lorenz-96 benchmarks demonstrate CTT’s superior causal time-series discovery capabilities, outperforming recent methods. Evaluations on ETH-UCY, nuScenes, and TrajAir datasets further show significant gains in multi-target prediction accuracy over baselines. Overall, CTT offers a robust, interpretable framework aligning inferred causal attributions with underlying drivers of multi-target time-series data.