Model-Free Counterfactual Subset Selection at Scale
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917919982616576 |
|---|---|
| author | Nguyen, Minh Hieu Doan, Viet Hung Nguyen, Anh Tuan Jo, Jun Nguyen, Quoc Viet Hung |
| author_facet | Nguyen, Minh Hieu Doan, Viet Hung Nguyen, Anh Tuan Jo, Jun Nguyen, Quoc Viet Hung |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Model-Free Counterfactual Subset Selection at Scale Nguyen, Minh Hieu Doan, Viet Hung Nguyen, Anh Tuan Jo, Jun Nguyen, Quoc Viet Hung Machine Learning Databases Data Structures and Algorithms Information Retrieval 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. |
| title | Model-Free Counterfactual Subset Selection at Scale |
| topic | Machine Learning Databases Data Structures and Algorithms Information Retrieval |
| url | https://arxiv.org/abs/2502.08326 |