Laixin is currently pursuing Ph.D. degree (supervised by Quan Li) at the School of Information Science and Technology, ShanghaiTech University.
My research interests span Social Network in Game and VIS4HPC (addressing HPC challengs via visual analytics approach). I design and implement visual analytics systems, deep learning algorithms (GNN, temporal models, interpretability methods), and empirical studies aimed at enhancing AIβs ability to serve human needs.
I am currently on the job market. If you have any relevant positions or opportunities, please feel free to reach out to me via email.
π₯ News
- 2023.07: Β ππ A poster Understanding Auto-Scheduling Optimizations for Model Deployment via Visualizations is accepted by VISβ23.
π Publications
RoleSeer: Understanding Informal Social Role Changes in MMORPGs via Visual Analytics
Laixin Xie, Ziming Wu, Peng Xu, Wei Li, Xiaojuan Ma, Quan Li
- Researched on the informal social role in MMORPGs, cooperating with Tencent and Netease.
- Developed an adapted dynamic network embedding method to identify the potential informal roles from the perspective of behavioral interaction analysis
- Proposed a visual analytics system named RoleSeer to investigate the informal roles from the perspectives of behavioral interactions and depict their dynamic interconversions and transitions.
Towards Better Modeling With Missing Data: A Contrastive Learning-Based Visual Analytics Perspective
Laixin Xie, Yang Ouyang, Longfei Chen, Ziming Wu, Quan Li
- Researched how to leverage contrastive learning to address missing data, cooperating with Tencent.
- Proposed a contrastive learning-based framework, allowing label prediction with the presence of data missing and without any imputation.
- Further developedd a visual analytics system, CIVis to understand the training process of contrastive learning and iterative refinement.
- VFLens: Co-design the Modeling Process for Efficient Vertical Federated Learning via Visualization, Yun Tian, He Wang, Laixin Xie, Xiaojuan Ma, Quan Li, Chinese CHI 2022
- Object Detection of NAO Robot Based on a Spectrum Model, Laixin Xie, Chunhua Deng, ICIC 2018
- Dimensionality Deduction for Action Proposals: To Extract or to Select?, Jian Jiang, Haoyu Wang, Laixin Xie, Junwen Zhang, Chunhua Deng, ICIC2018
π Educations
- 2020.09 - present, PhD, ShanghaiTech University, Shanghai
- 2015.09 - 2019.06, Undergraduate, Wuhan University of Science and Technology, Wuhan
π» Internships
- 2021.12 - 2022.6, Interactive Entertainment Group (IEG) in Tencent (Supervised by Ziming Wu), Shenzhen
- 2022.11 - 2023.9, User eXperience (UX) in Netease, Shanghai
- 2023.09 - present, Hong Kong University of Science and Technology (HKUST), Supervised by Xiaojuan Ma, Hong Kong