用注意力机制直接从时间序列中发现因果关系，还能大幅减少模型参数。
Mask2Cause: Causal Discovery via Adjacency Constrained Causal Attention
- 通过约束邻接关系的注意力机制，端到端学习因果图结构。
- 在多种真实和合成数据上表现领先，参数量比基线少很多。
- 发现的因果结构可让预测模型减参超70%，精度不降。
利用深度学习进行时间序列因果发现仍具挑战性，因现有神经方法多依赖逐变量架构，无法捕捉共享系统动态，或采用解耦后处理图提取，易受虚假相关性干扰。我们提出Mask2Cause，一种在预测前向传播中直接恢复底层因果图的端到端框架。该方法引入反向变量嵌入与邻接约束掩码注意力机制，通过同方差或异方差目标训练，同时捕捉均值与方差中的因果影响。在多样基准测试中，包括合成混沌动力学与真实生物模拟，均达到最先进性能，且相比标准基线显著降低参数复杂度。进一步表明，推断出的因果结构可使预测模型平均减少超过70%的参数量，同时保持预测精度。
原文摘要 · Abstract (English)
Leveraging deep learning for causal discovery in time series remains challenging because existing neural methods predominantly rely on component-wise architectures that fail to capture shared system dynamics or employ decoupled post-hoc graph extraction that risks overfitting to spurious correlations. We propose $\textbf{Mask2Cause}$, an end-to-end framework that recovers the underlying causal graph directly during the forecasting forward pass. Our approach introduces an Inverted Variable Embedding and an Adjacency-Constrained Masked Attention mechanism, trained with homoscedastic or heteroscedastic objectives to capture causal influences in both mean and variance. Empirical results on diverse benchmarks, from synthetic chaotic dynamics to realistic biological simulations, demonstrate state-of-the-art causal discovery with significantly reduced parameter complexity compared to standard baselines. We further show that inferred causal structures can be used to reduce parameter count of forecasting models by more than 70% on average while maintaining predictive accuracy.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。