Dynamic Sparse Causal-Attention Temporal Networks for Interpretable Causality Discovery in Multivariate Time Series

• URL: http://arxiv.org/abs/2507.09439v1
• Date: Sun, 13 Jul 2025 01:03:27 GMT
• Title: Dynamic Sparse Causal-Attention Temporal Networks for Interpretable Causality Discovery in Multivariate Time Series
• Authors: Meriem Zerkouk, Miloud Mihoubi, Belkacem Chikhaoui,
• Abstract summary: We introduce Dynamic Sparse Causal-Attention Temporal Networks for Interpretable Causality Discovery in MTS (DyCAST-Net)<n>DyCAST-Net is a novel architecture designed to enhance causal discovery by integrating dilated temporal convolutions and dynamic sparse attention mechanisms.<n>We show that DyCAST-Net consistently outperforms existing models such as TCDF, GCFormer, and CausalFormer.
• Score: 0.4369550829556578
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding causal relationships in multivariate time series (MTS) is essential for effective decision-making in fields such as finance and marketing, where complex dependencies and lagged effects challenge conventional analytical approaches. We introduce Dynamic Sparse Causal-Attention Temporal Networks for Interpretable Causality Discovery in MTS (DyCAST-Net), a novel architecture designed to enhance causal discovery by integrating dilated temporal convolutions and dynamic sparse attention mechanisms. DyCAST-Net effectively captures multiscale temporal dependencies through dilated convolutions while leveraging an adaptive thresholding strategy in its attention mechanism to eliminate spurious connections, ensuring both accuracy and interpretability. A statistical shuffle test validation further strengthens robustness by filtering false positives and improving causal inference reliability. Extensive evaluations on financial and marketing datasets demonstrate that DyCAST-Net consistently outperforms existing models such as TCDF, GCFormer, and CausalFormer. The model provides a more precise estimation of causal delays and significantly reduces false discoveries, particularly in noisy environments. Moreover, attention heatmaps offer interpretable insights, uncovering hidden causal patterns such as the mediated effects of advertising on consumer behavior and the influence of macroeconomic indicators on financial markets. Case studies illustrate DyCAST-Net's ability to detect latent mediators and lagged causal factors, making it particularly effective in high-dimensional, dynamic settings. The model's architecture enhanced by RMSNorm stabilization and causal masking ensures scalability and adaptability across diverse application domains

Related papers

• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• Multiresolution Analysis and Statistical Thresholding on Dynamic Networks [49.09073800467438]
  ANIE (Adaptive Network Intensity Estimation) is a multi-resolution framework designed to automatically identify the time scales at which network structure evolves.<n>We show that ANIE adapts to the appropriate time resolution and is able to capture sharp structural changes while remaining robust to noise.
  arXiv  Detail & Related papers  (2025-06-01T22:55:55Z)
• Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency [59.05753942719665]
  We propose a novel temporal robustness benchmark (TemRobBench) to assess the robustness of models.<n>We evaluate 16 mainstream LMMs and find that they exhibit over-reliance on prior knowledge and textual context in adversarial environments.<n>We design panoramic direct preference optimization (PanoDPO) to encourage LMMs to incorporate both visual and linguistic feature preferences simultaneously.
  arXiv  Detail & Related papers  (2025-05-20T14:18:56Z)
• Beyond Patterns: Harnessing Causal Logic for Autonomous Driving Trajectory Prediction [10.21659221112514]
  We introduce a novel trajectory prediction framework that leverages causal inference to enhance predictive robustness, generalization, and accuracy.<n>Our findings highlight the potential of causal reasoning to transform trajectory prediction, paving the way for robust autonomous driving systems.
  arXiv  Detail & Related papers  (2025-05-11T05:56:07Z)
• Model Hemorrhage and the Robustness Limits of Large Language Models [119.46442117681147]
  Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment.<n>We define this phenomenon as model hemorrhage - performance decline caused by parameter alterations and architectural changes.
  arXiv  Detail & Related papers  (2025-03-31T10:16:03Z)
• An AI-powered Bayesian generative modeling approach for causal inference in observational studies [4.624176903641013]
  CausalBGM is an AI-powered Bayesian generative modeling approach.<n>It estimates the individual treatment effect (ITE) by learning individual-specific distributions of a low-dimensional latent feature set.
  arXiv  Detail & Related papers  (2025-01-01T06:52:45Z)
• Robust Time Series Causal Discovery for Agent-Based Model Validation [5.430532390358285]
  This study proposes a Robust Cross-Validation (RCV) approach to enhance causal structure learning for ABM validation. We develop RCV-VarLiNGAM and RCV-PCMCI, novel extensions of two prominent causal discovery algorithms. The proposed approach is then integrated into an enhanced ABM validation framework.
  arXiv  Detail & Related papers  (2024-10-25T09:13:26Z)
• Neural Networks Decoded: Targeted and Robust Analysis of Neural Network Decisions via Causal Explanations and Reasoning [9.947555560412397]
  We introduce TRACER, a novel method grounded in causal inference theory to estimate the causal dynamics underpinning DNN decisions. Our approach systematically intervenes on input features to observe how specific changes propagate through the network, affecting internal activations and final outputs. TRACER further enhances explainability by generating counterfactuals that reveal possible model biases and offer contrastive explanations for misclassifications.
  arXiv  Detail & Related papers  (2024-10-07T20:44:53Z)
• SFANet: Spatial-Frequency Attention Network for Weather Forecasting [54.470205739015434]
  Weather forecasting plays a critical role in various sectors, driving decision-making and risk management. Traditional methods often struggle to capture the complex dynamics of meteorological systems. We propose a novel framework designed to address these challenges and enhance the accuracy of weather prediction.
  arXiv  Detail & Related papers  (2024-05-29T08:00:15Z)
• On the Identification of Temporally Causal Representation with Instantaneous Dependence [50.14432597910128]
  Temporally causal representation learning aims to identify the latent causal process from time series observations. Most methods require the assumption that the latent causal processes do not have instantaneous relations. We propose an textbfIDentification framework for instantanetextbfOus textbfLatent dynamics.
  arXiv  Detail & Related papers  (2024-05-24T08:08:05Z)
• A comparative assessment of deep learning models for day-ahead load forecasting: Investigating key accuracy drivers [2.572906392867547]
  Short-term load forecasting (STLF) is vital for the effective and economic operation of power grids and energy markets. Several deep learning models have been proposed in the literature for STLF, reporting promising results.
  arXiv  Detail & Related papers  (2023-02-23T17:11:04Z)
• On the benefits of robust models in modulation recognition [53.391095789289736]
  Deep Neural Networks (DNNs) using convolutional layers are state-of-the-art in many tasks in communications. In other domains, like image classification, DNNs have been shown to be vulnerable to adversarial perturbations. We propose a novel framework to test the robustness of current state-of-the-art models.
  arXiv  Detail & Related papers  (2021-03-27T19:58:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.