Research map / Time series / Causal and generative time series
Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models
Chirag Raman, Alec Nonnemaker, Amelia Villegas-Morcillo, Hayley Hung, Marco Loog
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace DeepSHAP with the entropy-based saliency framework | saliency computation for forecasts · Group leaving (MatchNMingle) | execution time: 13.5 min -> 2 ms | Improved |
| replace DeepSHAP with the entropy-based saliency framework | saliency computation for forecasts · Vehicle trajectory (nuScenes) | execution time: 26.3 min -> 33 ms | Improved |
| use perfect forecasting model with entropy saliency | saliency framework · synthetic turn-taking data | identifies true salient timesteps 138 and 139 | Improved |
| use real Social Process forecaster instead of perfect forecasts | saliency framework · synthetic turn-taking data | identifies true salient timesteps | Improved |
| compare against DeepSHAP, GradientSHAP, IntegratedGradients, SmoothGrad | attribution on forecast mean and std · synthetic turn-taking data | capturing salient predictive relationships | Hurt |
| compare against DeepSHAP and GradientSHAP | attribution on forecast mean and std · MatchNMingle group leaving | intuitive patterns | No clear effect |
Closest papers by meaning
- Counterfactual-based Saliency Map: Towards Visual Contrastive Explanations for Neural Networks (ICCV 2023 · similarity 0.87)
- Learning Perturbations to Explain Time Series Predictions (ICML 2023 · similarity 0.86)
- LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching (NeurIPS 2025 · similarity 0.86)
- Explaining Time Series via Contrastive and Locally Sparse Perturbations (ICLR 2024 · similarity 0.85)
- Explainable Saliency: Articulating Reasoning with Contextual Prioritization (CVPR 2025 · similarity 0.85)
- TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
