I am a final-year PhD student in Computer Science at University of Illinois, Urbana Champaign. I am working in the Data Mining Group under Prof. Jiawei Han.
In my research, I develop data-driven, weakly supervised, and scalable techniques for knowledge discovery over massive, complex, and noisy network (graph) data. My interests span graph data mining, network data science, and applied machine learning, with a focus on designing novel graph analysis and deep learning frameworks for the effective construction, modeling, and application of real-world network data, towards tasks like conditional stucture generation, contextualized network embedding, and graph-aided recommendations.
Before joining UIUC, I received my Bachelor of Engineering Degree in Computer Science in 2014, from the Chu Kochen Honors College, Zhejiang University. I was working in the State Key Lab of CAD&CG on machine learning with Prof. Xiaofei He.
[2020.05] My work in collaboration with researchers in Pinterest and Stanford on web-scale contextualized graph neural networks has been accepted by KDD 2020 ADS track (oral 5.8%).
[2020.05] My work in collaboration with researchers in UIUC and POSTECH (South Korea) on differentiable multi-aspect network embedding has been accepted by KDD 2020 Research track.
[2020.05] I am honored to receive the UIUC 2020 Doctoral Dissertation Completion Fellowship ($20,000), which is awarded to 20 candidates (from 20 departments) out from 74 nominations (from 48 departments) across the whole university.
[2020.05] I will be joining Emory University Dept. of Computer Science as a tenure-track Assistant Professor in September this year. Cor prudentis possidebit scientiam!
[2020.04] I am visiting University of Oxford and collaborating with Prof. Thomas Lukasiewicz and his team on structured information extraction from multi-media data this summer.
[2020.04] Our pioneering work on neural end-to-end text-to-graph generation has been accepted by SIGIR 2020.
[2020.04] My collaboration with researchers in Sun Yat-sen University on adversarial perturbation in discrete data has led to a full paper accepted by SIGIR 2020.
[2020.04] My work with students in UIUC on GNN aggregation mechanisms has been accepted by IJCAI 2020. Congratulations to the authors!
[2020.03] Our survey and benchmark project towards heterogeneous network representation learning has been released on Arxiv and GitHub.
[2020.02] I will deliver research talks in Emory University, University of Florida and University of Sydney.
[2020.01] I am visiting my alma mater, Zhejiang University, for the first time after my graduation five years ago.
[2019.11] I will deliver research talks in Northwestern University, Simon Fraser University, and University of British Columbia.
[2019.10] Our collaboration with LinkedIn Economic Graph Research has led to another paper accepted by WSDM 2020 (after CIKM 2019).
[2019.09] I am invited to attend and give a talk in the Great Lakes Workshop on Data Science.
[2019.09] My work with students in UIUC on conditional graph generation has been accepted by NeurIPS 2019.
[2019.08] My two new leading research papers on context-rich network construction have been accepted by CIKM 2019 and ICDM 2019.
[2019.07] The Han Family will get together in San Francisco. Happy birthday Prof Han!
[2019.06] Our demo about Cube Networks has been accepted by KDD 2019.
[2019.05] I am working in Pinterest Lab this summer with the Applied Science team led by Prof. Jure Leskovec.
Empowered GraphSage for web-scale contextualized recommendation through context-aware aggregation and Hadoop-based stream training on heterogeneous pin-board networks.
Developed a two-step data-driven pipeline of feature generation and metric learning for place embedding to leverage ad-hoc place attributes and noisy training data towards efficient place deduplication.
Constructed the transportation HIN (heterogeneous information network) based on DiDi's travel data and developed a pattern-aware HIN embedding algorithm for passenger experience prediction.
Developed a joint learning framework of user links and attributes for friend recommendation and interest targeting. Implemented a Spark pipeline and scaled it to networks with millions of nodes and billions of edges.
Implemented data extraction and inventory analysis pipeline using flume C++. Implemented an online simulation of ads serving and an offline optimal algorithm based on max flow to analyze the inventory.