Welcome to Hsiang-Fu Yu's Home Page

My name is Hsiang-Fu Yu. I am a Principal Applied Scientist at Amazon and a Ph.D. graduated from the Center of Big Data Analytics of University of Texas at Austin supervised by Prof. Inderjit Dhillon. I received my master degree in National Taiwan University with a supervision of Prof. Chih-Jen Lin. My research mainly focus on machine learning and data mining. Please see my Curriculum Vitae for further information.

E-Mail: rofuyu_AT_cs.utexas.edu

Education

Ph.D., Department of Computer Science, University of Texas at Austin, 2011 - 2016.

National Taiwan University, Taipei, Taiwan

M.S., Department of Computer Science and Information Engineering, 2008 - 2010
B.S., Department of Computer Science and Information Engineering, 2004 - 2008

Work Experience

Amazon, Palo Alto, U.S. (Oct 2016 - now)

Principal Applied Scientist
Leading the PECOS project to develop solutions for various projects requiring Predictions for Enormous and Correlated Output Spaces (github)
Worked on deep learning modeling for personalized recommendation
Worked on recurrent behavior modeling and context-aware personalization
Worked on query completion problems in search

Microsoft Research, Redmond, U.S. (Jun 2015 - Aug 2015)

Research Intern
Worked on one-class collabrative filtering problems

WalmartLabs., San Bruno, U.S. (Jun 2013 - Aug 2013)

Research Intern
Advised by Manyam Mallela now at Blueshift

EBay Inc., San Jose, U.S. (May 2012 - Aug 2012)

Research Intern
Investigated large-scale product title classification
Conducted analysis on the feedback given by buyers.

Google Inc., Taipei, Taiwan/Mountain View, U.S. (Jun 2008 - Sep 2008)

Engineering Intern
Worked on the projet of universal search.
Investigated machine learning approaches for boosting CTR of universal search results.

Institute of Plant and Microbial Biology, Academia Sinica, Taiwan (Mar 2008 - May 2008)

Research assistent.

National Center for Theoretical Sciences, Taiwan (Jul 2005 - Aug 2005, Jul 2006 - Aug 2006)

Summer Intern
Studied on graph coloring and related problems
Studied on Ramsey Theory and related problems

Publications

Jyun-Yu Jiang, Wei-Cheng Chang, Jiong Zhang, C.-J. Hsieh, H.-F. Yu Relevance under the Iceberg: Reasonable Prediction for Extreme Multi-label Classification. To Appear at SIGIR, 2022.

Y. Xiong, W.-C. Chang, C.-J. Hsieh, H.-F. Yu, I. S. Dhillon. Extreme Zero-Shot Learning for Extreme Text Classification. To Appear North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2022.

H.-F Yu, K. Zhong, J. Zhang, W.-C. Chang, and I. S. Dhillon. PECOS: Prediction for Enormous and Correlated Output Spaces. Journal of Machine Learning Research (JMLR), 2022.

P. A. Etter, K. Zhong, H.-F Yu, L. Ying, and I. S. Dhillon. Accelerating Inference for Sparse Extreme Multi-Label Ranking Trees. ACM International Conference on World Wide Web (WWW), 2022.

E. Chien, W.-C. Chang, C.-J. Hsieh, H.-F Yu, J. Zhang, O. Milenkovic, I. S. Dhillon. Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction. International Conference on Learning Representations (ICLR), 2022.

J. Zhang, W.-C. Chang, H.-F Yu, I. S. Dhillon. Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification. Advances in Neural Information Processing Systems (NeurIPS) 34, 2021.

X. Liu, W.-C. Chang, H.-F Yu, C.-J. Hsieh, and I. S. Dhillon. Label Disentanglement in Partition-based Extreme Multilabel Classification. Advances in Neural Information Processing Systems (NeurIPS) 34, 2021.

P.-H. Chen, H.-F Yu, C.-J. Hsieh, and I. S. Dhillon. DRONE: Data-aware Low-rank Compression for Large NLP Models. Advances in Neural Information Processing Systems (NeurIPS) 34, 2021.

W.-C. Chang, D. Jiang, H.-F. Yu, C.-H. Teo, J. Zhang, K. Zhong, K. Kolluri, Q. Hu, N. Shandilya, V. Ievgrafov, J. Singh, and I. S. Dhillon. Extreme Multi-label Learning for Semantic Matching in Product Search. The conference on Knowledge, Discovery, and Data Mining (KDD), 2021.

X. Liu, H.-F Yu, I. S. Dhillon, and C.-J. Hsieh. Learning to Encode Positions with Continuous Dynamical Model. International Conference of Machine Learning (ICML) 37, 2020.

Y. Shen, H.-F Yu, S. Sanghavi, and I. S. Dhillon. Extreme Multi-label Classification from Aggregated Labels. International Conference of Machine Learning (ICML) 37, 2020.

W.-C. Chang, H.-F. Yu, K. Zhong, Y. Yang, and I. S. Dhillon. Taming Pretrained Transformers for eXtreme Multi-label Text Classification. The conference on Knowledge, Discovery, and Data Mining (KDD), 2020. Code

L. Wu, H.-F. Yu, N. Rao, J. Sharpnack, and C.-J. Hsieh. Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.

Q. Hu, H.-F Yu, V. Narayanan, I. Davchev, R. Bhagat, and I. S. Dhillon. Query Transformation for Multi-Lingual Product Search. The 2020 SIGIR Workshop On eCommerce.

R. Sen, H.-F. Yu, and I. S. Dhillon. Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting. Advances in Neural Information Processing Systems (NeurIPS), 2019. An earlier version appears in Time Series Workshop at ICML 2019. Code

J. Zhang, H.-F. Yu, and I. S. Dhillon. AutoAssist: A Framework to Accelerate Training of Deep Neural Networks. Advances in Neural Information Processing Systems (NeurIPS), 2019. Code.

Qin Ding, H.-F. Yu, and C.-J. Hsieh. A Fast Sampling Algorithm for Maximum Inner Product Search. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

P. Raman, J. Zhang, S. Ji, H.-F. Yu, S V N Vishwanathan, and I. S. Dhillon. Extreme Stochastic Variational Inference: Distributed Inference for Large Scale Mixture Models. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

H.-F. Yu, C.-J. Hsieh, and I. S. Dhillon. Parallel Asynchronous Stochastic Coordinate Descent with Auxiliary Variables. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019.

W.-C. Chang, H.-F. Yu, I. S. Dhillon, and Y. Yang. SeCSeq: Semantic Coding for Sequence-to-Sequence based Extreme Multi-label Classification. NIPS Workshop: Compact Deep Neural Network Representation with Industrial Applications (NIPS CDNNRIA), 2018.

C. Jiang, H.-F. Yu, C.-J. Hsieh, and Kai-Wei Chang. Learning Word Embeddings for Low-resource Languages by PU Learning. North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2018. Code.

H.-F. Yu, C.-J. Hsieh, Q. Lei, and I. S. Dhillon. A Greedy Approach for Budgeted Maximum Inner Product Search. Advances in Neural Information Processing Systems (NIPS) 30, 2017. Supplementary materials are in the end of the paper. Code.

H.-F. Yu, H.-Y Huang, I. S. Dhillon, and C.-J. Lin. A Unified Algorithm for One-class Structured Matrix Factorization with Side Information. AAAI Conference on Artificial Intelligence (AAAI) 31, 2017. Supplementary materials are in the end of the paper. Code.

H.-F. Yu, M. Bilenko, and C.-J. Lin. Selection of negative samples for one-class matrix factorization. SIAM International Conference on Data Mining (SDM), 2017. Code.

Y. You, X. Lian, J. Liu, H.-F. Yu, I. S. Dhillon, J. Demmel, and C.-J. Hsieh. Asynchronous Parallel Greedy Coordinate Descent. Advances in Neural Information Processing Systems (NIPS) 29, 2016.

H.-F. Yu, N. Rao, and I. S. Dhillon. Temporal Regularized Matrix Factoriztion for High-dimensional Time Series Prediction. Advances in Neural Information Processing Systems (NIPS) 29, 2016. A preliminary version appear appears at Time Series Workshop at NIPS 2015. Code.

H.-F. Yu, C.-J. Hsieh, H. Yun, S V N Vishwanathan, and I. S. Dhillon. Nomadic Computing for Big Data Analytics. IEEE Computer. vol. 49:4, pages 52-60, 2016.

N. Rao, H.-F. Yu, P. Ravikumar, and I. S. Dhillon. Collaborative Filtering with Graph Information: Consistency and Scalable Methods. Advances in Neural Information Processing Systems (NIPS) 28, 2015. Spotlight. Code.

C.-J. Hsieh, H.-F. Yu, and I. S. Dhillon. PASSCoDe:Parallel ASynchronous Stochastic dual Co-ordinate Descent. International Conference of Machine Learning (ICML) 32, 2015. Code, Slides.

H.-F. Yu, C.-J. Hsieh, H. Yun, S V N Vishwanathan, and I. S. Dhillon. A Scalable Asynchronous Distributed Algorithm for Topic Modeling. ACM International Conference on World Wide Web (WWW), 2015. Code.

H. Yun, H.-F. Yu, C.-J. Hsieh, S V N Vishwanathan, and I. S. Dhillon. NOMAD: Non-locking stOchastic Multi-machine algorithm for Asynchrounous and Descentralized matrix completion. Very Large Data Base (VLDB), 2014.

H.-F. Yu, P. Jain, P. Kar, and I. S. Dhillon. Large-scale Multi-label Learning with Missing Values. International Conference on Machine Learning (ICML) 31, 2014. Pre-built Binary Code, Source Code with Inductive Matrix Factorization Extension.

H.-F. Yu, C.-J. Hsieh, S. Si, and I. S. Dhillon. Parallel Matrix Factorization for Recommender Systems. Knowledge and Information Systems (KAIS), 41(3), 793--819, 2014.

H.-F. Yu, C.-H. Ho, Y.-C. Juan, and C.-J. Lin. LibShortText: a library for short-text classification and analysis. Technical report 2013. LibShortText software.

H.-F. Yu, C.-H. Ho, P. Arunachalam, M. Somaiya, and C.-J. Lin. Product Title Classification versus Text Classification. Technical report 2012.

H.-F. Yu, C.-J. Hsieh, S. Si, and I. S. Dhillon. Scalable Coordinate Descent Approaches to Parallel Matrix Factorization for Recommender Systems. IEEE International Conference on Data Mining(ICDM), December 2012, best paper award.

H.-F. Yu, C.-J. Hsieh, K.-W. Chang, and C.-J. Lin. Large linear classification when data cannot fit in memory. KDD 2010 best research paper award. code. A short version appears in IJCAI 2011. A journal version appears in ACM Transactions on Knowledge Discovery from Data (TKDD), Volumn 5 Issue 4 (2012).

H.-F. Yu, F.-L. Huang, and C.-J. Lin. Dual coordinate descent methods for logistic regression and maximum entropy models. Machine Learning, 85(2011), 41-75. (Code)

H.-F. Yu, H.-Y. Lo, H.-P. Hsieh, J.-K. Lou, T. G. McKenzie, J.-W. Chou, P.-H. Chung, C.-H. Ho, C.-F. Chang, Y.-H. Wei, J.-Y. Weng, E.-S. Yan, C.-W. Chang, T.-T. Kuo, Y.-C. Lo, P.-T. Chang, C. Po, C.-Y. Wang, Y.-H. Huang, C.-W. Hung, Y.-X. Ruan, Y.-S. Lin, S.-D. Lin, H.-T. Lin, and C.-J. Lin. Feature Engineering and Classifier Ensemble for KDD Cup 2010. National Taiwan University, June 2010; submitted. (First Prizes of Both All Teams and All Student Team)

H.-Y. Lo, K.-W. Chang, S.-T. Chen, T.-H. Chiang, C.-S. Ferng, C.-J. Hsieh, Y.-K. Ko, T.-T. Kuo, H.-C. Lai, K.-Y. Lin, C.-H. Wang, H.-F. Yu, C.-J. Lin, H.-T. Lin and S.-d. Lin. An Ensemble of Three Classifiers for KDD Cup 2009: Expanded Linear Model, Heterogeneous Boosting, and Selective Naive Bayes. JMLR Workshop and Conference Proceedings V.7, 57-64, 2009 (Third Place of the KDDCup'09 Slow Track).

Software

PECOS:
PECOS is a versatile and modular machine learning (ML) framework for fast learning and inference on problems with large output spaces, such as extreme multi-label ranking (XMR) and large-scale retrieval.
LIBPMF:
A parallel matrix factorization library. It's very fast for large-scale data.
LibShortText:
A Library for Short-text Classification and Analysis
LIBLINEAR:
A linear support vector machine (SVM) library. It's very fast for large-scale data.

Selected Awards

Intel Ph.D. Fellowship. 2014-2015.
Best Paper Award at IEEE ICDM 2012.
Best Research Paper Award at ACM KDD 2010.
First Prizes of Both All Teams and All Student Teams at KDD Cup 2010.
Best Master's Thesis Award, TAAI, 2010.
Third Prize in the ``slow'' track at KDD Cup 2009.
Winner in SVM track of PASCAL Large Scale Learning Challenge at ICML 2008 workshop
Honorary member of the Phi Tau Phi Scholastic Honor Society (top 3% among 140 graduate students)
Presidential Award at National Taiwan University, 8 times (top 5% among 118 undergraduate students)