Scalable Counterfactual Explanations for Time Series via Policy Learning
cs.LG, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-09
Comments: Accepted at IEEE Big Data 2026
Code: https://github.com/Luckilyeee/PLCF
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generating counterfactual (CF) explanations for time series is challenging due to complex temporal dependencies and the computational inefficiency of traditional instance-specific optimization.
Abstract
Generating counterfactual (CF) explanations for time series is challenging due to complex temporal dependencies and the computational inefficiency of traditional instance-specific optimization. We propose a policy learning framework for counterfactual explanation in time series, trained as a one-step contextual-bandit policy-learning problem. By training an actor-critic agent in the latent space of a pre-trained autoencoder, our method learns a transferable policy that captures global structural regularities. Unlike existing methods that rely on iterative optimization for each new input, the learned policy enables direct generation of valid and plausible counterfactuals through a single forward pass, avoiding per-instance optimization at inference time. Experiments on 13 UCR benchmark datasets show that our framework achieves high validity and strong plausibility across multiple anomaly detection metrics. Overall, by decoupling counterfactual generation from per-instance optimization, the proposed method provides an efficient and scalable alternative to existing approaches for time series counterfactual explanations.
Sources
- Motif-guided Time Series Counterfactual Explanations
- Shapelet-Based Counterfactual Explanations for Multivariate Time Series
- Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning
- Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Prediction
- Continuous control with deep reinforcement learning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis