Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models
We propose a post hoc saliency-based explanation framework for counterfactual reasoning in probabilistic multivariate time-series forecasting (regression) settings. Building upon Miller's framework of explanations derived from research in multiple social science disciplines, we establish a conceptual link between counterfactual reasoning and saliency-based explanation techniques. To address the lack of a principled notion of saliency, we leverage a unifying definition of information-theoretic saliency grounded in preattentive human visual cognition and extend it to forecasting settings. Specifically, we obtain a closed-form expression for commonly used density functions to identify which observed timesteps appear salient to an underlying model in making its probabilistic forecasts. We empirically validate our framework in a principled manner using synthetic data to establish ground-truth saliency that is unavailable for real-world data. Finally, using real-world data and forecasting models, we demonstrate how our framework can assist domain experts in forming new data-driven hypotheses about the causal relationships between features in the wild.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Why Did This Model Forecast This Future? Closed-Form Temporal Saliency Towards Causal Explanations of Probabilistic Forecasts
Forecasting tasks surrounding the dynamics of low-level human behavior are of significance to multiple research domains. In such settings, methods for explaining specific forecasts can enable domain experts to gain insig…
AttributeFormvalidWhat if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions
Time series forecasting has become increasingly critical in real-world scenarios, where future sequences are influenced not only by historical patterns but also by forthcoming events. In this context, forecasting must dy…
Time Series ForecastingA Game-Theoretic Framework for Joint Forecasting and Planning
Planning safe robot motions in the presence of humans requires reliable forecasts of future human motion. However, simply predicting the most likely motion from prior interactions does not guarantee safety. Such forecast…
Temporal Saliency Detection Towards Explainable Transformer-based Timeseries Forecasting
Despite the notable advancements in numerous Transformer-based models, the task of long multi-horizon time series forecasting remains a persistent challenge, especially towards explainability. Focusing on commonly used s…
DecoderSaliency DetectionTime SeriesTime Series Analysis+3DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Series
Time-series forecasting increasingly demands not only accurate observational predictions but also causal forecasting under interventional and counterfactual queries in multivariate systems. We present DoFlow, a flow-base…
Anomaly Detection