Mask2Cause: Causal Discovery via Adjacency Constrained Causal Attention
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SC3D: Dynamic and Differentiable Causal Discovery for Temporal and Instantaneous Graphs
Discovering causal structures from multivariate time series is a key problem because interactions span across multiple lags and possibly involve instantaneous dependencies. Additionally, the search space of the dynamic g…
LLM-initialized Differentiable Causal Discovery
The discovery of causal relationships between random variables is an important yet challenging problem that has applications across many scientific domains. Differentiable causal discovery (DCD) methods are effective in …
BenchmarkingCausal DiscoveryCan We Utilize Pre-trained Language Models within Causal Discovery Algorithms?
Scaling laws have allowed Pre-trained Language Models (PLMs) into the field of causal reasoning. Causal reasoning of PLM relies solely on text-based descriptions, in contrast to causal discovery which aims to determine t…
Causal DiscoveryCASTLE: Regularization via Auxiliary Causal Graph Discovery
Regularization improves generalization of supervised models to out-of-sample data. Prior works have shown that prediction in the causal direction (effect from cause) results in lower testing error than the anti-causal di…
BayesDAG: Gradient-Based Posterior Inference for Causal Discovery
Bayesian causal discovery aims to infer the posterior distribution over causal models from observed data, quantifying epistemic uncertainty and benefiting downstream tasks. However, computational challenges arise due to …
Causal DiscoveryVariational Inference