π¨βπ« About Me
Hi, I am Haoyi Xiao (θθ±ͺε₯), a second-year B.S. student majoring in Computer Science and Technology at Guangdong University of Technology (GDUT), advised by Prof. Yiqun Zhang. I conduct research in the SIGMTA group at the OMG Lab. My research focuses on unsupervised machine learning, multivariate time-series clustering, and representation learning. I have published three papers at SIGKDD, BIBM, and ICIC.
I have participated in five Student Innovation Training Program projects, including three national-level projects and two provincial-level projects, as well as one provincial science and technology innovation project. I currently serve as a reviewer for IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI).
π₯ News
- π 2026/06: Approved to lead a national-level Student Innovation Training Program project.
- π 2026/05: One paper accepted at SIGKDD 2026.
- π 2026/03: Won the Grand Prize in the Huashang Zhiyan Global AI Scenario Innovation Competition.
- π 2025/09: One paper accepted at BIBM 2025.
- π 2025/09: Won a provincial second prize in the China Undergraduate Mathematical Contest in Modeling.
- π 2025/07: Won the National First Prize in the Chinese Collegiate Computing Competition (4C), the highest award at the national finals.
- π 2025/05: One paper accepted at ICIC 2025.
π Publications
AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE
Tao Xie, Zexi Tan, Haoyi Xiao, Mengke Li, Yiqun Zhang, Yang Lu, Cuie Yang, Yiu-ming Cheung
An interpretable mixture-of-experts framework that uses anchor-based routing to connect time-series representations, attribution segments, and expert decisions.
DE3S: Dual-Enhanced Soft-Sparse-Shape Learning for Medical Early Time-Series Classification
Tao Xie, Zexi Tan, Haoyi Xiao, Binbin Sun, Yiqun Zhang
A dual-enhanced framework for medical early time-series classification, combining patch-level enhancement, sparsification, and expert fusion to support reliable early prediction.
MACL: Metric and Attribute Space Co-learning for Qualitative Data Clustering
Haoyi Xiao, Xinxi Chen, Xiaopeng Luo, Xiang Zhang, Gengwen Huang, Wei Ai
ICIC 2025 Β· Paper
A metric and attribute space co-learning approach for qualitative data clustering.
π¨βπ Education
π Honors
- Grand Prize, Huashang Zhiyan Global AI Scenario Innovation Competition
- National First Prize, 18th Chinese Collegiate Computing Competition (4C) (the highest award at the national finals)
- Provincial Second Prize, China Undergraduate Mathematical Contest in Modeling
Service
- βComputing Meets Intangible Cultural Heritageβ summer social practice project for rural communities, conducted under the High-Quality Development Project for Counties, Towns, and Villages
Contact
Feel free to contact me at xiaohaoyi1@mails.gdut.edu.cn to discuss time-series analysis, unsupervised learning, research collaboration, or open-source projects.
You can also find my work on Google Scholar, GitHub, DBLP, and ORCID.