Model-Free Counterfactual Subset Selection at Scale

2025-02-12

AI Summary

To address synthetic-data bias, full-dataset dependency, and real-time bottlenecks in counterfactual explanation for streaming data, this paper proposes the first model-agnostic, synthetic-sample-free framework for large-scale streaming counterfactual subset selection. Our method leverages online submodular optimization and dynamic core-set maintenance, integrating a joint diversity–relevance metric—without requiring gradients, generative models, or distributional assumptions. It enables storage-free, real-time updates with O(log k) time complexity per arrival. Extensive experiments on multiple real-world and synthetic streaming datasets demonstrate a 32% improvement in explanation quality (F1-score) over state-of-the-art baselines, while maintaining robustness under adversarial perturbations and efficiently scaling to million-item streams.

Technology Category

• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization
• Data Mining & Knowledge Management: Data Stream Mining

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Ensuring transparency in AI decision-making requires interpretable explanations, particularly at the instance level. Counterfactual explanations are a powerful tool for this purpose, but existing techniques frequently depend on synthetic examples, introducing biases from unrealistic assumptions, flawed models, or skewed data. Many methods also assume full dataset availability, an impractical constraint in real-time environments where data flows continuously. In contrast, streaming explanations offer adaptive, real-time insights without requiring persistent storage of the entire dataset. This work introduces a scalable, model-free approach to selecting diverse and relevant counterfactual examples directly from observed data. Our algorithm operates efficiently in streaming settings, maintaining $O(log k)$ update complexity per item while ensuring high-quality counterfactual selection. Empirical evaluations on both real-world and synthetic datasets demonstrate superior performance over baseline methods, with robust behavior even under adversarial conditions.

Problem

• model-free counterfactual subset selection
• real-time streaming explanations
• bias-free interpretable AI decisions

Innovation

• Model-free counterfactual selection
• Streaming data processing
• Efficient O(log k) update