Zhao Zihao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhao Zihao has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Daochen Zha
Airbnb, San Francisco, USA
1 shared publication - Junnan Dong
The Hong Kong Polytechnic University, Hung Hom, Hong Kong
1 shared publication - Qiaoyu Tan
New York University Shanghai, Shanghai, China
1 shared publication - Qinggang Zhang
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
1 shared publication - Xiao Huang
The Hong Kong Polytechnic University, Hong Kong, Hong Kong
1 shared publication
Latest Publications
- Open Access
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 877-885
Active Ensemble Learning for Knowledge Graph Error Detection
Knowledge graphs (KGs) could effectively integrate a large number of real-world assertions, and improve the performance of various applications, such as recommendation and search. KG error detection has been intensively studied since real-world KGs inevitably contain erroneous triples. While existing studies focus on developing a novel algorithm dedicated to one or a few data characteristics, we explore advancing KG error detection by assembling a set of state-of-the-art (SOTA) KG error detectors. However, it is nontrivial to develop a practical ensemble learning framework for KG error detection. Existing ensemble learning models heavily rely on labels, while it is expensive to acquire labeled errors in KGs. Also, KG error detection itself is challenging since triples contain rich semantic information and might be false because of various reasons. To this end, we propose to leverage active learning to minimize human efforts. Our proposed framework - KAEL, could effectively assemble a set of off-the-shelf error detection algorithms, by actively using a limited number of manual annotations. It adaptively updates the ensemble learning policy in each iteration based on active queries, i.e., the answers from experts. After all annotation budget is used, KAEL utilizes the trained policy to identify remaining suspicious triples. Experiments on real-world KGs demonstrate that we can achieve significant improvement when applying KAEL to assemble SOTA error detectors. KAEL also outperforms SOTA ensemble learning baselines significantly.
- 27 February 2023
- Published by Association for Computing Machinery (ACM)
- p. 877-885
Open AccessActive Ensemble Learning for Knowledge Graph Error Detection
Knowledge graphs (KGs) could effectively integrate a large number of real-world assertions, and improve the performance of various applications, such as recommendation and search. KG error detection has been intensively studied since real-world KGs inevitably contain erroneous triples. While existing studies focus on developing a novel algorithm dedicated to one or a few data characteristics, we explore advancing KG error detection by assembling a set of state-of-the-art (SOTA) KG error detectors. However, it is nontrivial to develop a practical ensemble learning framework for KG error detection. Existing ensemble learning models heavily rely on labels, while it is expensive to acquire labeled errors in KGs. Also, KG error detection itself is challenging since triples contain rich semantic information and might be false because of various reasons. To this end, we propose to leverage active learning to minimize human efforts. Our proposed framework - KAEL, could effectively assemble a set of off-the-shelf error detection algorithms, by actively using a limited number of manual annotations. It adaptively updates the ensemble learning policy in each iteration based on active queries, i.e., the answers from experts. After all annotation budget is used, KAEL utilizes the trained policy to identify remaining suspicious triples. Experiments on real-world KGs demonstrate that we can achieve significant improvement when applying KAEL to assemble SOTA error detectors. KAEL also outperforms SOTA ensemble learning baselines significantly.