Yezi Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Yezi Liu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Hanning Chen
University of California, Irvine, Irvine, California, USA
3 shared publications - Mohsen Imani
UC Irvine
3 shared publications - Yanning Shen
Department of Electrical Engineering and Computer Science, University of California, Irvine, CA, USA
3 shared publications - Wenjun Huang
University of California Irvine
2 shared publications - Yang Ni
Purdue University Northwest, Hammond, Indiana, USA
2 shared publications - Hyun Woo Oh
University of California, Irvine, Irvine, California, USA
1 shared publication
Latest Publications
- Open Access
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 447-457
Debias Once for All: A Data-Centric Strategy for Fair Machine Learning
- 21 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 447-457
Open AccessDebias Once for All: A Data-Centric Strategy for Fair Machine Learning
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1925-1935
Enabling Group Fairness in Machine Unlearning via Distribution Correction
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1925-1935
Open AccessEnabling Group Fairness in Machine Unlearning via Distribution Correction
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3932-3941
LVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3932-3941
Open AccessLVLM_CSP: Accelerating Large Vision Language Models via Clustering, Scattering, and Pruning for Reasoning Segmentation
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1143-1147
Beyond Node Condensation: Learning Tiny Graphs via Joint Graph Condensation
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1143-1147
Open AccessBeyond Node Condensation: Learning Tiny Graphs via Joint Graph Condensation
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1138-1142
White Admitted by Stanford, Black Got Rejections: Exploring Racial Stereotypes in Text-to-Image Generation from a College Admissions Lens
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 1138-1142
Open AccessWhite Admitted by Stanford, Black Got Rejections: Exploring Racial Stereotypes in Text-to-Image Generation from a College Admissions Lens
- Open Access
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4135-4139
FairGraph: Automated Graph Debiasing with Gradient Matching
- 21 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 4135-4139
Open AccessFairGraph: Automated Graph Debiasing with Gradient Matching
- Open Access
- 17 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 2590-2599
Contrastive Knowledge Graph Error Detection
Knowledge Graph (KG) errors introduce non-negligible noise, severely affecting KG-related downstream tasks. Detecting errors in KGs is challenging since the patterns of errors are unknown and diverse, while ground-truth labels are rare or even unavailable. A traditional solution is to construct logical rules to verify triples, but it is not generalizable since different KGs have distinct rules with domain knowledge involved. Recent studies focus on designing tailored detectors or ranking triples based on KG embedding loss. However, they all rely on negative samples for training, which are generated by randomly replacing the head or tail entity of existing triples. Such a negative sampling strategy is not enough for prototyping practical KG errors, e.g., (Bruce_Lee, place_of_birth, China), in which the three elements are often relevant, although mismatched. We desire a more effective unsupervised learning mechanism tailored for KG error detection. To this end, we propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED). It introduces contrastive learning into KG learning and provides a novel way of modeling KG. Instead of following the traditional setting, i.e., considering entities as nodes and relations as semantic edges, CAGED augments a KG into different hyper-views, by regarding each relational triple as a node. After joint training with KG embedding and contrastive learning loss, CAGED assesses the trustworthiness of each triple based on two learning signals, i.e., the consistency of triple representations across multi-views and the self-consistency within the triple. Extensive experiments on three real-world KGs show that CAGED outperforms state-of-the-art methods in KG error detection. Our codes and datasets are available at https://github.com/Qing145/CAGED.git.
- 17 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 2590-2599
Open AccessContrastive Knowledge Graph Error Detection
Knowledge Graph (KG) errors introduce non-negligible noise, severely affecting KG-related downstream tasks. Detecting errors in KGs is challenging since the patterns of errors are unknown and diverse, while ground-truth labels are rare or even unavailable. A traditional solution is to construct logical rules to verify triples, but it is not generalizable since different KGs have distinct rules with domain knowledge involved. Recent studies focus on designing tailored detectors or ranking triples based on KG embedding loss. However, they all rely on negative samples for training, which are generated by randomly replacing the head or tail entity of existing triples. Such a negative sampling strategy is not enough for prototyping practical KG errors, e.g., (Bruce_Lee, place_of_birth, China), in which the three elements are often relevant, although mismatched. We desire a more effective unsupervised learning mechanism tailored for KG error detection. To this end, we propose a novel framework - ContrAstive knowledge Graph Error Detection (CAGED). It introduces contrastive learning into KG learning and provides a novel way of modeling KG. Instead of following the traditional setting, i.e., considering entities as nodes and relations as semantic edges, CAGED augments a KG into different hyper-views, by regarding each relational triple as a node. After joint training with KG embedding and contrastive learning loss, CAGED assesses the trustworthiness of each triple based on two learning signals, i.e., the consistency of triple representations across multi-views and the self-consistency within the triple. Extensive experiments on three real-world KGs show that CAGED outperforms state-of-the-art methods in KG error detection. Our codes and datasets are available at https://github.com/Qing145/CAGED.git.