Jiayi Xu
Papers
1
Total Citations
41
H-Index
1
About
Jiayi Xu is a leading researcher in visual analytics and machine learning interpretability, with a particular focus on making complex models transparent and accessible. Her seminal work, "EasySVM: A visual analysis approach for open-box support vector machines" (2017), which has garnered 41 citations, pioneered a novel framework that transforms the traditionally opaque SVM classification process into an interactive, visually guided experience. By enabling users to explore decision boundaries, support vectors, and parameter effects in real time, Xu’s contribution bridges the gap between high-performance machine learning and human understanding, empowering analysts to validate, debug, and trust model outcomes. This work stands as a cornerstone in the emerging field of explainable AI, demonstrating how visualization can demystify black-box algorithms without sacrificing accuracy. Xu’s research not only advances theoretical foundations but also provides practical tools for data scientists and domain experts, fostering more responsible and informed use of AI in critical applications. Her achievements highlight a commitment to democratizing machine learning, making her a pivotal figure for students and researchers seeking to build interpretable, human-centered intelligent systems.
Research Focus
Key Achievements
Top Papers
- 1EasySVM: A visual analysis approach for open-box support vector machines41 citations · 2017