{"type":"ScholarlyArticle","title":"Fast Explanations via Policy Gradient-Optimized Explainer","authors":[{"name":"Deng Pan","slug":"deng-pan","given":"Deng","family":"Pan","affiliation":""},{"name":"Nuno Moniz","slug":"nuno-moniz","given":"Nuno","family":"Moniz","affiliation":""},{"name":"Nitesh V. Chawla","slug":"nitesh-v-chawla","given":"Nitesh V.","family":"Chawla","affiliation":""}],"abstract":"The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert's knowledge of specific model structures that trade general applicability for efficiency. To address these limitations, this paper introduces a novel framework Fast EXplanation (FEX) that represents attribution-based explanations via probability distributions, which are optimized by leveraging the policy gradient method. The proposed framework offers a robust, scalable solution for real-time, large-scale model explanations, bridging the gap between efficiency and applicability.\r\nWe validate our framework on image and text classification tasks and the experiments demonstrate that our method reduces inference time by over 97 percent and memory usage by 70 percent compared to traditional model-agnostic approaches while maintaining high-quality explanations and broad applicability.","doi":"10.24963/ijcai.2025/54","url":"https://ijcai.org/proceedings/2025/54","pdf":"https://ijcai.org/proceedings/2025/0054.pdf","markdown":"https://ijcai.org/proceedings/2025/54.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/54","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"AI Ethics, Trust, Fairness","track":"Main Track","number":54,"pages":{"first":475,"last":483},"keywords":["AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","Natural Language Processing: NLP: Interpretability and analysis of models for NLP","Computer Vision: CV: Interpretability and transparency"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}