132 citations
- Huawei Technologies (China)CN16 papers
- McGill UniversityCA6 papers
- University of OttawaCA6 papers
- University of WaterlooCA6 papers
- University of AlbertaCA5 papers
- Carleton UniversityCA4 papers
- Queen's UniversityCA4 papers
- University of TorontoCA4 papers
- City University of Hong KongHK3 papers
- Southern University of Science and TechnologyCN3 papers
- Université de MontréalCA3 papers
- York UniversityCA3 papers
Showing 2022 · cs.LGShow all
3 papers · 2 filters
cs.LG2022★ 132 cited
The impact of feature importance methods on the interpretation of defect classifiers
Gopi Krishnan Rajbahadur, Shaowei Wang, Yasutaka Kamei +1
Classifier specific (CS) and classifier agnostic (CA) feature importance methods are widely used (often interchangeably) by prior studies to derive feature importance ranks from a…
cs.LG2022★ 47 cited
Towards Training Reproducible Deep Learning Models
Boyuan Chen, Mingzhi Wen, Yong Shi +4
Reproducibility is an increasing concern in Artificial Intelligence (AI), particularly in the area of Deep Learning (DL). Being able to reproduce DL models is crucial for AI-based…
cs.LG2022★ 29 cited
Towards a consistent interpretation of AIOps models
Yingzhe Lyu, Gopi Krishnan Rajbahadur, Dayi Lin +3
Artificial Intelligence for IT Operations (AIOps) has been adopted in organizations in various tasks, including interpreting models to identify indicators of service failures. To a…