Lucas Vinh Tran

Senior Applied Research Scientist, Apple

About Me

[Twitter] [LinkedIn] [Google Scholar]

Biography: I am currently a Senior Applied Research Scientist at Apple, under Apple Media Products (AMP) AI+ML Recommendations team. My team builds personalization, ranking, and recommender systems for App Store, Video (TV App), Music, Podcasts and Books. We also power content understanding and features discovery, as well as on-device architectures across Apple Media Products.

Previously, I obtained my Ph.D. in Computer Science from Nanyang Technological University (NTU), under A*STAR Computing & Information Science Scholarship (ACIS) and A*STAR Graduate Scholarship (AGS), supervised by Prof. Gao Cong (@NTU) and Dr. Xiaoli Li (@A*STAR). I was also affiliated with the Machine Intellection Department of Institution for Infocomm Research (I2R), A*STAR. Prior to that, I was graduated with B.Sc. in Mathematical Sciences from the same university in 2016.

Research Interests: My main research interests include (applied) machine learning, deep learning, differentiable generative models and high-dimensional statistics. At present, I am broadly interested in representation learning (Euclidean and non-Euclidean representation), especially in the applications of recommender systems (personalized and group recommendation). I am also expanding my research knowledge in online learning, federated and on-device machine learning.

Publications

* : equal contribution
  1. HME: A Hyperbolic Metric Embedding Approach for Next-POI Recommendation. Shanshan Feng, Lucas Vinh Tran, Gao Cong, Lisi Chen, Jing Li, and Fan Li. In the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020. [PDF] (Acceptance rate: 147/555 = 26.47%)

  2. HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems. Lucas Vinh Tran, Yi Tay, Shuai Zhang, Gao Cong, and Xiaoli Li. In the 13th ACM International Conference on Web Search and Data Mining (WSDM), 2020. [PDF] (Acceptance rate: 91/615 = 14.80%) (Best Paper Award Runner-Up)

  3. Quaternion Collaborative Filtering for Recommendation. Shuai Zhang, Lina Yao, Lucas Vinh Tran, Aston Zhang, and Yi Tay. In the 28th International Joint Conference on Artificial Intelligence (IJCAI), 2019. [PDF] (Acceptance rate: 850/4752 = 17.89%)

  4. Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation. Lucas Vinh Tran, Tuan-Anh Nguyen Pham, Yi Tay, Yiding Liu, Gao Cong, and Xiaoli Li. In the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2019. [PDF] (Acceptance rate: 84/426 = 19.72%)

  5. Holographic Factorization Machines for Recommendation. Yi Tay*, Shuai Zhang*, Anh Tuan Luu, Siu Cheung Hui, Lina Yao, and Lucas Vinh Tran. In the 33th AAAI Conference on Artificial Intelligence (AAAI), 2019. [PDF] (Acceptance rate: 1150/7095 = 16.21%)

Work Experience

Apple

Apple Media Products (AMP) AI+ML -- Recommendations

Senior Applied Research Scientist, Singapore, May. 2020 - Present

A*STAR - Agency for Science, Technology and Research

Institute for Infocomm Research (I2R) -- Machine Intellection Department

Machine Learning Researcher, Singapore, Aug. 2016 - May. 2020

Facebook

APAC Global Gaming

Gaming Data Scientist, Singapore, May. 2015 - Aug. 2015

Education

Nanyang Technological University

School of Computer Science and Engineering (SCSE) -- Data Management and Analytics Lab (DMAL) / Data Management @ Nanyang Tech (DANTE) Group

Ph.D. in Computer Science, Singapore, Aug. 2016 - May. 2020

Nanyang Technological University

School of Physical and Mathematical Sciences (SPMS)

B.Sc. in Mathematical Sciences, Singapore, Aug. 2012 - May. 2016

Professional Services

Program Comittee (PC) / Invited Reviewer:

  • Conference: ICLR'21, ICML'21, AAAI'21, CIKM'21, EMNLP'21, ACL'21, NeurIPS'20, ICML'20, WSDM'20, ACL'20, IJCAI'20, NeurIPS'19

External Reviewer:

  • Conference: NeurIPS, KDD, WWW, SIGIR, WSDM, EMNLP, ACL, AAAI, IJCAI, ICDE, CIKM, ICDM, SIGSPATIAL, DASFAA

  • Journal: TKDE, TIST, TOIS, TNNLS, JASIST

Invited/Guest Speaker:

  • "Attention-based Models for Personalized Game Recommendations". Apple Machine Learning Summit. Recommendations and Personalization (R&P) Track. Cupertino, USA. Jan. 26, 2021

  • "Efficient and Effective Group Recommendation: Challenges and Solutions". Nanyang Technological University. Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU). Singapore, Singapore. Aug. 19, 2019

Conference Talks:

  • "HyperML: A Boosting Metric Learning Approach in Hyperbolic Space for Recommender Systems". Best Paper Award Session. WSDM'20. Texas, USA. Feb. 06, 2020

  • "Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation". Recommendations Session. SIGIR'19. Paris, France. Jul. 22, 2019

Consultant:

  • Stealth Blockchain Startup: Predict land acquisition on Decentralized market for LAND. 2018 - 2019

  • Private Bank: Increase open, reaction, and redemption rate for bank offers to card holders. 2017 - 2018

Honours & Awards

  • ICML 2020 Top Reviewer Award

  • WSDM 2020 Best Paper Award Runner-Up

  • ACM SIGIR 2019 Student Travel Grant

  • A*STAR Computing and Information Science Scholarship (ACIS)

  • A*STAR Graduate Scholarship (AGS)

Miscellaneous

  • Group Recommender Systems: Research Papers, Datasets and Source Code [Link]

  • Deep Learning based Recommender System: A Survey and New Perspectives [Link]

  • Libraries for deep learning based recommendation models [Link 1][Link 2][Link 3][Link 4][Link 5]

  • Benchmark Public Datasets for Recommender Systems [Link 1][Link 2]

  • Comprehensive reading lists for new ML/DL research students [Link]

  • Computer Science Conference Ranking List [Link 1][Link 2]

Contact

  • Email: A@B, where A=lucasvinhtran and B=gmail.com