Kai Yang(杨凯)

PhD Candidate

Harbin Institute of Technology (Shenzhen)
Supervisor: Prof. Xun Zhou
IEEE & ACM Student Member

Research interests: Spatial-temporal Data Mining, Recommendation System, Trustworthy AI

Email: kaiyang.cs AT outlook.com
[Google Scholar] [GitHub]

Short Bio

Recent News

• [2026/08] 1 paper accepted by IEEE ICDM 2026.
• [2026/07] 1 paper submitted to SIGKDD 2027.
• [2026/06] 1 paper accepted by ACM MM 2026.
• [2026/01] 1 paper submitted to ACM TOIS.
• [2025/12] 1 paper submitted to ACM TKDD.
• [2025/09] Joined HITSZ as a PhD Candidate.
• [2025/06] Graduated from UESTC.
• [2024/10] Received the National Scholarship.
• [2024/10] Received the First-class Scholarship of UESTC.
• [2024/04] ICASSP 2024 Presentation in Seoul, South Korea.
• [2024/03] 1 paper accepted by SIGIR 2024.
• [2023/12] 3rd place, China People's Net AI Algorithm Competition.
• [2023/12] Received China Shenzhen Stock Exchange Scholarship.
• [2023/11] 1 paper accepted by ICASSP 2024.
• [2023/10] 2 papers accepted by AAAI 2024.

Selected Publications

SHAPE: Spatial Hyperbolic-Embedding Augmented Pretraining for Estimated Time of Arrival on Obfuscated Trajectories
Ruopu Li, Yong Chu, Kai Yang, James Jianqiao Yu, Lixia Wu, Xun Zhou
ICDM 2026, CCF-B

SHAPE is a spatial hyperbolic-embedding augmented pretraining framework for estimated time of arrival on obfuscated trajectories, which learns robust route representations via differential geometric feature decomposition and hybrid Euclidean-hyperbolic contrastive self-supervised learning.

RoPOI: Robust POI Recommendation based on Modality Disentanglement and Missing Representation Generation
Kai Yang, Xun Zhou
ACM MM 2026, CCF-A

RoPOI is a robust point-of-interest recommendation framework built on modality disentanglement and missing representation generation, which mitigates performance degradation from modality absence while preserving discriminative modality-specific information.

ExNext: Self-Explainable Next POI Recommendation [Paper] [Code]
Kai Yang, Yi Yang, Qiang Gao, Ting Zhong, Yong Wang, Fan Zhou
SIGIR 2024, CCF-A

ExNext is a self-explainable POI recommendation framework that improves trustworthiness by balancing accuracy and explainability, leveraging information theory to learn compact, informative representations.

ExGeo: Exploring Self-Explainable Street-Level IP Geolocation with Graph Information Bottleneck [Paper] [Code]
Kai Yang, Wenxin Tai, Zhenhui Li, Ting Zhong, Guangqiang Yin, Yong Wang, Fan Zhou
ICASSP 2024, CCF-B

ExGeo endows the IP geolocation model with explainability via a variational graph information bottleneck, balancing concise explanation and informative representation.

TCGeo: Improving IP Geolocation With Target-Centric IP Graph (Student Abstract) [Paper]
Kai Yang, Jiayang Li, Wenxin Tai, Zhenhui Li, Ting Zhong, Guangqiang Yin, Yong Wang, Fan Zhou
AAAI 2024, Student Abstract

A target-centric IP graph is proposed to mitigate sparsity, enhancing contextual information utilization in network topology for geolocation.

LSGAT: Interpreting Temporal Knowledge Graph Reasoning (Student Abstract) [Paper]
Bin Chen, Kai Yang, Wenxin Tai, Zhangtao Cheng, Leyuan Liu, Ting Zhong, Fan Zhou
AAAI 2024, Student Abstract

An interpretable temporal knowledge graph reasoning method with competitive prediction accuracy, which identifies pivotal historical events for explainability.

Honors

• Outstanding Graduate, Sichuan Province2025
• National Scholarship of China 2024
• First-class Academic Scholarship of UESTC 2024
• China Shenzhen Stock Exchange Scholarship 2023
• 3rd Place, China People's Net AI Algorithm Competition 2023

Services

• Conference Reviewer: ICLR, AAAI, KDD
• Journal Reviewer: IEEE TKDE