Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
원문 초록
Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and learning is done in an incremental rather than a batch mode. We seek efficient incremental algorithms for computing feature importance (FI) measures, specifically, an incremental FI measure based on feature marginalization of absent features similar to permutation feature importance (PFI). We propose an efficient, model-agnostic algorithm called iPFI to estimate this measure incrementally and under dynamic modeling conditions including concept drift. We prove theoretical guarantees on the approximation quality in terms of expectation and variance. To validate our theoretical findings and the efficacy of our approaches compared to traditional batch PFI, we conduct multiple experimental studies on benchmark data with and without concept drift.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generation
Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods
Machine Learning Meets Transparency in Osteoporosis Risk Assessment: A Comparative Study of ML and Explainability Analysis
Explaining the Unexplainable: A Systematic Review of Explainable AI in Finance
Leveraging Explainable AI for LLM Text Attribution: Differentiating Human-Written and Multiple LLMs-Generated Text
토론
이 논문과 연결된 포럼 글이 아직 없습니다.