Zijie Huang (黄子倢)

I am currently a Ph.D. candidate at University of California, Los Angeles (UCLA), where I am fortunate to be advised by Prof.Yizhou Sun and Prof.Wei Wang. My research interest lies in graph neural networks and machine learning in general, with a special focus on reasoning over dynamical systems (graphs) and knowledge graph modeling. My research is generously supported by Amazon Ph.D. Fellowship.

Before joinging UCLA, I received my bachelor's degree of Information Engineering from Shanghai Jiao Tong University (SJTU) in 2019. I love piano, badminton and traveling.

Email  /  linkedin  /  Github  /  Google Scholar

profile photo

Ph.D.          Sep. 2019 - Present
                       University of California Los Angeles (UCLA), Los Angeles, CA, U.S.
                       Ph.D. student in Computer Science

B.S.              Sep. 2015 - June 2019
                       Shanghai Jiao Tong University (SJTU), Shanghai, China.
                       B.S. in Information Engineering
Intern Experience
  • Jun 2022 -- Sep 2022, Amazon Product Graph Team (PG), Seattle, WA
    Applied Scientist Intern

  • Jun 2021 -- Sep 2021, Amazon Search (A9), Bay Area, CA
    Applied Scientist Intern

  • Jan.2019 -- May.2019, eBay , Shanghai, China
    Software Engineer Intern

  • Jun.2018 -- Oct.2018, University of Illinois at Urbana-Champaign (UIUC) , Urbana, IL
    Reseach Intern

prl Generalizing Graph ODE for Learning Complex System Dynamics across Environments
Zijie Huang, Yizhou Sun and Wei Wang
The Conference on Knowledge Discovery and Data Mining (KDD), 2023

We proposed a generalized graphODE framework for predicting multi-agent system dynamics across different envrionments.

prl CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems
Song Jiang,Zijie Huang, Xiao Luo and Yizhou Sun
The Conference on Knowledge Discovery and Data Mining (KDD), 2023

We proposed a novel graphODE framework for making counterfactual predictions of multi-agent dynamical systems.

prl Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs
Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun and Wei Wang
Annual Meeting of the Association for Computational Linguistics (ACL-Findings), 2023

We proposed a novel geometric representation learning framework for learning two-view knowledge graphs and constructed a recipe-related two-view KG dataset.

prl HOPE: High-order Graph ODE For Modeling Interacting Dynamics
Xiao Luo, Jingyang Yuan, Zijie Huang, Huiyu Jiang, Yifang Qin, Wei Ju, Ming Zhang, Yizhou Sun
International Conference on Machine Learning (ICML), 2023

We proposed a higher-order graphODE framework to improve model effectiveness on various dynamical system downstream tasks.

prl Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
Zijie Huang, Zheng Li, Haoming Jiang, Tianyu Cao, Hanqing Lu, Bing Yin, Karthik Subbian, Yizhou Sun, Wei Wang
Annual Meeting of the Association for Computational Linguistics (ACL), 2022

We proposed a multilingual knowledge graph completion model and constructed an e-commercial multilingual KG dataset.
[Paper] [Code] [Slides]

prl Coupled Graph ODE for Learning Interacting System Dynamics
Zijie Huang, Yizhou Sun, Wei Wang
The Conference on Knowledge Discovery and Data Mining (KDD), 2021

We proposed coupled graph ODE (CG-ODE) for modeling the co-evolution of graph nodes and edges in a continuous manner.
[Paper] [Code] [Slides]

prl DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction
Ruijie Wang, Zijie Huang, Shengzhong Liu, Huajie Shao, Dongxin Liu, Jinyang Li, Tianshi Wang, Dachun Sun,Shuochao Yao, Tarek Abdelzaher
The International ACM SIGIR Conference on Research and Developmentin Information Retrieval (SIGIR), 2021

We proposed a generative model that considers user dynamic interest and text contents to predict cascade diffusioin on social network.

blind-date Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
Zijie Huang, Yizhou Sun, Wei Wang
The Conference on Neural Information Processing Systems (NeurIPS), 2020

We proposed latent graph ODE (LG-ODE) to learn system dynamics from irregularly-sampled and partial observations with underlying graph structure.
[Paper] [Code] [Slides]

clean-usnob Weakly Supervised Attention for Hashtag Recommendation using Graph Data
Amin Javari, Zhankui He, Zijie Huang, Raj Jeetu, Kevin Chen-Chuan Chang
The Web Conference (WWW) , 2020

We built a novel weak supervision model that jointly considers user interactions and hashtag text contents for hashtag recommendation.

Academic Services
  • PC member of KDD2020, SSL@WWW2021, AAAI2022

  • Journal/Conference Reviewer: TKDD 2020, AAAI 2021, KDD2021, ICDM2021, KDD2022

  • Teaching Assistant, Introduction to Data Mining, Wei Wang. UCLA, 2021 Spring

  • Teaching Assistant, Introduction to Computer Science I (C++), Bruce Huang. UCLA, 2021 Winter

  • Teaching Assistant, Introduction to Data Mining, Yizhou Sun. UCLA, 2020 Fall

  • ICML Student Travel Award, 2023

  • Amazon & UCLA Science Hub Fellowship, 2022.

  • NeurIPS Student Travel Award, 2020.

  • National Scholarship, 2017.

  • Outstanding Graduate of Shanghai Jiao Tong University, 2019.

  • Chunstung Scholarship, 2018.

  • Yongling Liu Scholarship, 2018.

  • Meritorious Winner, Mathematics Contest in Modeling, 2017.

  • Academic Excellence Scholarship of SJTU, 2016,2017,2018.

Website Template