Illuminating the Black Box: An Interpretable Machine Learning Based on Ensemble Trees

doi:10.1016/j.eswa.2025.126720

淡江大學機構典藏 > 工學院 > 資訊工程學系暨研究所 > 期刊論文 > Item 987654321/126777

請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/126777

題名:	Illuminating the Black Box: An Interpretable Machine Learning Based on Ensemble Trees
作者:	Lee, Yue-Shi;Yen, Show-Jane;Jiang, Wendong;Chen, Jiyuan;Chang, Chih-Yung
關鍵詞:	Interpretable machine learning;Machine learning;Explanation
日期:	2025-05-05
上傳時間:	2025-03-20 09:24:24 (UTC+8)
摘要:	Deep learning has achieved significant success in the analysis of unstructured data, but its inherent black-box nature has led to numerous limitations in security-sensitive domains. Although many existing interpretable machine learning methods can partially address this issue, they often face challenges such as model limitations, interpretability randomness, and a lack of global interpretability. To address these challenges, this paper introduces an innovative interpretable ensemble tree method, EnEXP. This method generates a sample set by applying fixed masking perturbation to individual samples, then constructs multiple decision trees using bagging and boosting techniques and interprets them based on the importance outputs of these trees, thereby achieving a global interpretation of the entire dataset through the aggregation of all sample insights. Experimental results demonstrate that EnEXP possesses superior explanatory power compared to other interpretable methods. In text processing experiments, the bag-of-words model optimized by EnEXP outperformed the GPT-3 Ada fine-tuned model.
關聯:	Expert System With Applications 272,，頁126720
DOI:	10.1016/j.eswa.2025.126720
顯示於類別:	[資訊工程學系暨研究所] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	30	檢視/開啟

在機構典藏中所有的資料項目都受到原著作權保護.

TAIR相關文章

資料載入中.....