I am an Assistant Professor of Computer Science at Emory University. Before that, I received my Ph.D. in Computer Science at the University of Illinois, Urbana Champaign, where I was working in the Data Mining Group led by Prof. Jiawei Han. Further before, I received my B.Eng. in Computer Science in 2014, from the Chu Kochen Honors College of Zhejiang University, where I was working in the State Key Lab of CAD&CG under Prof. Xiaofei He.
My research interests lie in graph data mining, applied machine learning, knowledge graphs and federated learning, as well as their applications in recommender systems, social networks, neurocience and healthcare.
[2023.04] We will be organizing the 2nd International Workshop on Federated Learning with Graph Data (FedGraph2023) at the ICDM 2023 conference. Please stay tuned as we construct the workshop website!
[2023.03] We will be conducting a tutorial for BrainGB during the ICIBM 2023 conference in Tampa, FL, on June 18th.
[2023.02] Many thanks to NIH NIDDK for funding my K25 award on Understanding Diabetes Heterogeneity via Mining Multimodality Interconnected Data. The award could not have been possible without the help from my many colleagues and great mentor team Dr. Vicki Hertzberg, Dr. Ali Mohammed, Dr. Guillermo Umpierrez and Dr. Roy Simpson.
[2022.11] Our paper on EHR-based clinical predictions was selected as one of the two Best Papers at ML4H. Congratulations to Ran Xu and Yue Yu, and many thanks to Joyce Ho and Mohammed Ali!
[2022.09] It was a great pleasure to mentor Ms. Alexis Li from Hamilton High School at Chandler. Alexis will be taking her work under my mentorship on brain network mixup to the final competition of ISEF this year. Good luck Alexis!
[2022.08] Our research on FedGraph was selected to be funded by Amazon Research Awards.
[2022.08] Congratulations to FederatedScope-GNN on winning the ADS Best Paper Award of KDD 2022, and many thanks for the detailed featuring and integration of our FedSage and GCFL as the most representative FGL models in the platform.
[2022.07] I was happy to serve as a mentor for the KDD 2022 Undergraduate Consortium. Check out this interesting paper on per-node privacy of GCN written by my mentee at University of Virginia.
[2022.07] It was a great pleasure to serve as a mentor for our NSF REU/RET site on Computational Mathematics for Data Science at Emory this summer. Here goes a cute video made by my mentees and also check out their web post, poster and paper!
[2022.06] We will be organizing the 1st International Workshop on Federated Learning with Graph Data (FedGraph2022), at ACM CIKM 2022, in Atlanta Georgia this October. Various types of submissions are welcomed!
[2022.05] Our four papers got accepted by KDD 2022, all of which are based on our recent progress in healthcare and neuroscience informatics-- we have successfully applied modern graph learning techniques to electronic health records, mobile health data, brain imaging, and SEEG data. One of them (GraphDNA) was honored to receive the Best Paper Award of Health Day (3 in total). Congratulations, team!
[2022.04] We will be organizing the 1st International Workshop on Neural Network Models for Brain Connectome Analysis (BrainNN2022), at IEEE BigData 2022, in Osaka Japan this December. Various types of submissions are welcomed!
[2022.03] Our benchmark paper on GNNs for brain network analysis can be accessed on arXiv and the benchmark website is also fully available! ([2022.10] Update: the BrainGB paper is now accepted by IEEE TMI.)
[2021.09] Our four papers got accepted by NeurIPS 2021. Three of them were under my supervision-- FedSage (subgraph-level federated learning), GCFL (graph-level federated learning) and EGI (GNN transferability). FedSage was selected for a Spotlight Presentation (3%). Great work, team!
[2021.04] Our three papers on graph neural networks (secure graph generation, embedding dimension selection and robust neighborhood aggregation) have been accepted by IJCAI 2021.
[2020.12] Our survey and benchmark paper on heterogeneous network representation learning has been accepted by IEEE TKDE. All code and data are available at https://github.com/yangji9181/HNE.
[2020.10] I am honored to receive the Best Paper Award from ICDM 2020 (1 out from 930 submissions and 91 acceptances)! Check out the TaxoGAN paper.
[2020.05] Our work (MultiSage) 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] 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.
[2020.02] I will deliver research talks in Northwestern University, Simon Fraser University, University of British Columbia, 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.
[2019.09] I will give a talk in the Great Lakes Workshop on Data Science.
[2019.07] The Han Family will get together in San Francisco. Happy birthday Prof Han!
[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.
Developed a relation profiling algorithm based on multiple signals including user attributes, link structures and diffusive messages in the social network with novel multi-modal graph autoencoders.
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.