Luyu Qiu
University of Hong Kong
7 Papers
2 Citations
Luyu Qiu is an academic researcher from University of Hong Kong. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 1, co-authored 3 publications. Previous affiliations of Luyu Qiu include Huawei.
Chat about Author
Papers
A Survey of Data-driven and Knowledge-aware eXplainable AI
Xiao-Hui Li,Caleb Chen Cao,Yuhan Shi,Wei Bai,Han Gao,Luyu Qiu,Cong Wang,Yuanyuan Gao,Shenjia Zhang,Xun Xue,Lei Chen +10 more
TL;DR: A survey, reviewing and taxonomizing existing efforts from the view-point of DKE, summarizing their contribution, technical essence and comparative characteristics, and categorizing methods into data-driven methods where explanation comes from the task-related data, and knowledge-aware methods where extraneous knowledge is incorporated.
229
Generating Perturbation-based Explanations with Robustness to Out-of-Distribution Data
Luyu Qiu,Yi Yang,Caleb Chen Cao,Yueyuan Zheng,H. Ngai,Janet Hsiao,Lei Chen +6 more
- 25 Apr 2022
TL;DR: This work addresses the OoD issue by designing a simple yet effective module that can quantify the affinity between the perturbed data and the original dataset distribution and penalize the influences of unreliable OoD data for the perturbation samples by integrating the inlier scores and prediction results of the target models.
25
•Posted Content
Resisting Out-of-Distribution Data Problem in Perturbation of XAI.
Luyu Qiu,Yi Yang,Caleb Chen Cao,Jing Liu,Yueyuan Zheng,Hilary Hei Ting Ngai,Janet H. Hsiao,Lei Chen +7 more
TL;DR: Zhang et al. as discussed by the authors designed an additional module quantifying the affinity between the perturbed data and the original dataset distribution, which is integrated into the process of aggregation, and the solution is compatible with the most popular perturbation-based XAI algorithms, such as RISE, OCCLUSION, and LIME.
4
SAR2EO: A High-resolution Image Translation Framework with Denoising Enhancement
Jun Yu,Shenshen Du,Renjie Lu,Pengwei Li,Guochen Xie,Zhongpeng Cai,Keda Lu,Qing Ling,Cong Wang,Luyu Qiu,Wei-Cheng Zheng +10 more
TL;DR: SAR2EO as discussed by the authors adopts the coarse-to-fine generator, multi-scale discriminators, and improved adversarial loss in the pix2pixHD model to increase the synthesis quality.
GCF-RD: A Graph-based Contrastive Framework for Semi-Supervised Learning on Relational Databases
Runjin Chen,Tong Li,Yanyan Shen,Luyu Qiu,Kaidi Li,Caleb Chen Cao +5 more
- 17 Oct 2022
TL;DR: A novel graph-based contrastive framework for semi-supervised learning on relational databases achieving promising predictive classification performance with only a handful of labeled data and leveraging label information in contrastive learning to mitigate its negative effect in knowledge transfer on the supervised counterpart.
2