HKUST Business School
Research Interests
I am a Ph.D. candidate in Information Systems at the HKUST Business School, advised by Prof. Yi Yang. Before that, I received my M.Phil. in Computer Science and Engineering from HKUST, advised by Prof. Kai Chen (CSE Department), and my B.Eng. in Software Engineering from Sun Yat-sen University.
My research develops trustworthy and knowledge-aware machine learning for real-world data and regulatory settings, along two main streams: (1) Relational Graph Learning — LLM agents that reason over graphs, graph–LLM co-teaching, and structured representation learning; and (2) Regulatory Machine Learning — machine unlearning, patent intelligence, and privacy-aware learning for compliance-sensitive applications such as finance and anti-fraud. My work has appeared at ICLR, NAACL, and IEEE Transactions on Big Data.
Education
-
The Hong Kong University of Science and TechnologyHKUST Business SchoolPh.D. in Information SystemsSep. 2023 - present -
The Hong Kong University of Science and TechnologyDept. of Computer Science and EngineeringM.Phil. in Computer Science and Engineering
Advised by Prof. Kai ChenFeb. 2019 - Nov. 2021 -
Sun Yat-sen UniversitySchool of Software EngineeringB.Eng. in Software EngineeringAug. 2014 - Jun. 2018
Industry Experience
-
WeBankResearch InternJun. 2025 - Apr. 2026 -
HKUST Business SchoolResearch AssistantApr. 2022 - Sep. 2023
-
ClustarResearch InternFeb. 2020 - Jan. 2021 -
ClustarResearch InternApr. 2018 - Jan. 2019
-
TencentProduct Manager InternNov. 2017 - Feb. 2018
Honors & Awards
-
First-Class Academic Scholarship, Sun Yat-sen University2014 - 2018
News
Selected Publications (view all )
PatentsNET: Graph-Based Pretraining for Patent Analytics
Zhitao Yin, Yi Yang, Zhuoyi Peng, Zhenghan Zhang
Working paper. Major revision at a business journal Major Revision
A graph representation learning framework that models patent citation and ownership networks to jointly predict a patent's economic value and its litigation risk.
PatentsNET: Graph-Based Pretraining for Patent Analytics
Zhitao Yin, Yi Yang, Zhuoyi Peng, Zhenghan Zhang
Working paper. Major revision at a business journal Major Revision
A graph representation learning framework that models patent citation and ownership networks to jointly predict a patent's economic value and its litigation risk.
GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu, Lixin Fan, Yi Yang
Preprint. arXiv preprint 2026
A benchmark that systematically probes how well large language models perform inference over graph-structured data across a diverse suite of reasoning tasks.
GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
Zhuoyi Peng, Jingzhou Jiang, Hanlin Gu, Lixin Fan, Yi Yang
Preprint. arXiv preprint 2026
A benchmark that systematically probes how well large language models perform inference over graph-structured data across a diverse suite of reasoning tasks.
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
Zhuoyi Peng, Hanlin Gu, Lixin Fan, Yi Yang
Preprint. arXiv preprint 2026
A co-teaching framework in which an LLM and a GNN supervise each other, moving beyond a single fixed teacher to improve graph representation learning.
Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
Zhuoyi Peng, Hanlin Gu, Lixin Fan, Yi Yang
Preprint. arXiv preprint 2026
A co-teaching framework in which an LLM and a GNN supervise each other, moving beyond a single fixed teacher to improve graph representation learning.
Adversarial Mixup Unlearning
Zhuoyi Peng, Yixuan Tang, Yi Yang
International Conference on Learning Representations (ICLR) 2025
We regularize machine unlearning with synthesized mixup samples that simulate data most susceptible to catastrophic forgetting, achieving reliable removal without degrading retained knowledge.
Adversarial Mixup Unlearning
Zhuoyi Peng, Yixuan Tang, Yi Yang
International Conference on Learning Representations (ICLR) 2025
We regularize machine unlearning with synthesized mixup samples that simulate data most susceptible to catastrophic forgetting, achieving reliable removal without degrading retained knowledge.
Federated Meta Embedding Concept Stock Recommendation
Zhuoyi Peng, Yi Yang, Liu Yang, Kai Chen
IEEE Transactions on Big Data (TBD) 2024
A federated meta-embedding framework for concept-stock recommendation that learns transferable representations across institutions while keeping sensitive financial data local.
Federated Meta Embedding Concept Stock Recommendation
Zhuoyi Peng, Yi Yang, Liu Yang, Kai Chen
IEEE Transactions on Big Data (TBD) 2024
A federated meta-embedding framework for concept-stock recommendation that learns transferable representations across institutions while keeping sensitive financial data local.
Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs
Zhuoyi Peng, Yi Yang
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL Findings) 2024
We study patent phrase similarity and propose a graph-augmented approach that enriches each phrase with a retrieved phrase graph, capturing the technical semantics that isolated phrases miss.
Connecting the Dots: Inferring Patent Phrase Similarity with Retrieved Phrase Graphs
Zhuoyi Peng, Yi Yang
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL Findings) 2024
We study patent phrase similarity and propose a graph-augmented approach that enriches each phrase with a retrieved phrase graph, capturing the technical semantics that isolated phrases miss.