First Prize of Shanghai Open Data Innovation Research Competition (Top 1 among 65 teams), 2019

Third Prize of Shanghai Competition Area in China Undergraduate Mathematical Contest in Model, 2018

Third Prize of the Chinese Mathematics Competitions, 2018
Outstanding Students in Fudan University, 2018&2019&2020

First Prize of the National Olympiad in Informatics in Provinces (NOIP), 2015

Predicting the engagement of users in Online Social Network, Sep. 2021-Now

• Proposed a deep learning-based model to predict the engagement of users with the historical data of users.

• Applied temporal graph attention network to model the relationship among users and graph neural network and transformer to model the interests of users.

Detecting Malicious Accounts in Online Developer Communities, Oct. 2020 - Now
• Analysis user patterns in online developer communities, proposed a deep learning-based model for detecting malicious users.

• Applied Phased LSTM to model the historical behaviors of users, Structure Hole Theory to model the cooperation relationship among users and GNN to model the relationship between users and the repositories.

• Achieved a test AUC value of 0.916 on the GitHub dataset.

Under submission to IEEE Transactions on Knowledge and Data Engineering (TKDE).

Identifying Structural Hole Spanners in Online Social Networks, Feb. 2020 - Now
• Analysis structure hole spanners’ patterns, proposed a transformer-based model for identifying structural hole spanners.

• Also proposed a deep learning-based model for identifying structural hole spanners with TextCNN and GBDT2NN to leverage the cross-site linking function to enhance the identification.

• Achieved a test AUC value of 0.922 and 0.828 on the Yelp and Foursquare datasets.

Deep Learning-Based Missing Book Prediction System for Library, Aug. 2019 - Feb. 2020
• Proposed a deep learning-based model to analyze the circulation data of the library and predict whether the books are lost.

• Devised a model with MLP for statistical information of book and bi-LSTM and attention mechanism for temporal information.

• Achieved a test AUC value of 0.941 and a test F1-score of 0.884.

The First Prize of Shanghai Open Data Innovation Research Competition.

Distinguishing Focal Cortical Dysplasia From Glioneuronal Tumors In Patients With Epilepsy By Machine Learning, Aug. 2019 - Feb. 2020

• Collaborated in applying classical machine learning algorithms to classify focal cortical dysplasia (FCD) and glioneuronal tumors (GNTs).

• Achieved a test F1-score of 0.9492 and test AUC value of 0.9719.

Published in Frontiers in Neurology, section Epilepsy.

Distinguishing Focal Cortical Dysplasia from Glioneuronal Tumors in Patients with Epilepsy by Machine Learning.
Yi Guo, Yushan Liu, Wenjie Ming, Zhongjin Wang, Junming Zhu, Yang Chen, Lijun Yao, Meiping Ding and Chunhong Shen.
Frontiers in Neurology, 2020, 11:Article 548305.
[PDF]