Implementing local-explainability in Gradient Boosting Trees: Feature Contribution
Not on the map. Why?
Abstract (arXiv)
Gradient Boost Decision Trees (GBDT) is a powerful additive model based on tree ensembles. Its nature makes GBDT a black-box model even though there are multiple explainable artificial intelligence (XAI) models obtaining information by reinterpreting the model globally and locally. Each tree of the ensemble is a transparent model itself but the final outcome is the result of a sum of these trees and it is not easy to clarify. In this paper, a feature contribution method for GBDT is developed. The proposed method takes advantage of the GBDT architecture to calculate the contribution of each feature using the residue of each node. This algorithm allows to calculate the sequence of node decisions given a prediction. Theoretical proofs and multiple experiments have been carried out to demonstrate the performance of our method which is not only a local explicability model for the GBDT algorithm but also a unique option that reflects GBDTs internal behavior. The proposal is aligned to the contribution of characteristics having impact in some artificial intelligence problems such as ethical analysis of Artificial Intelligence (AI) and comply with the new European laws such as the General Data Protection Regulation (GDPR) about the right to explain and nondiscrimination.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 15 of its 35 references that are in the map. First posted on arXiv 14 Feb 2024.
Builds on
15 of 35 references.
References · 15
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2017Axiomatic Attribution for Deep Networkscited by 3,384
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 939
- 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
- 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
- 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 344
- 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
- 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 254
- 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
- 2017Learning how to explain neural networks: PatternNet and PatternAttributioncited by 84
- 2019Global Explanations of Neural Networks: Mapping the Landscape of Predictionscited by 32
3 more
- 2020Interpretable Machine Learning with an Ensemble of Gradient Boosting Machinescited by 14
- 2017Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagationcited by 10
- 2021On the Trustworthiness of Tree Ensemble Explainability Methodscited by 5
Built on by
Citing papers per year: 2024: 2.
2 papers.