• 7 Citations
  • 1 h-Index
20182019
If you made any changes in Pure these will be visible here soon.

Personal profile

Biography

I am a Lecturer of Computer Science at The University of Western Australia (UWA). Before working at UWA, I was a research fellow at National University of Singapore from 2017 to 2019 and The University of Melbourne from 2015 to 2016 after completion of my PhD degree at The University of Melbourne in 2015. My research work has led to open-source machine learning systems such as ThunderGBM and ThunderSVM.

Research interests

Machine Learning

  • systems for machine learning, automatic machine learning, learning with resource constraints

High-Performance Computing

  • modern hardware (e.g., GPUs and multi-core CPUs) acceleration, distributed computing in heterogeneous systems

Data Mining

  • medical data analytics, financial data mining, data mining platforms

More information is available at https://zeyiwen.github.io/

Current projects

ThunderGBM

  • supports classification, regression and ranking,
  • is often 10 times faster than XGBoost, LightGBM and CatBoost,
  • has attracted 430+ stars and 50+ forks on GitHub, and
  • is built on our related work: TPDS'19 and IPDPS'18.

ThunderSVM

  • supports all the functionalities of LibSVM including classification, regression and distribution estimation,
  • is often 10 to 100 times faster than LibSVM,
  • has attracted 1000+ stars and 140+ forks on GitHub, and
  • is built on these pieces of key related work: JMLR'18TKDE'18 and ICDM'14.

Community engagement

Reviewers

  • Journal of Machine Learning Research (JMLR), MLOSS track, 2018 & 2019
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2019
  • ACM Transactions on Knowledge Discovery from Data (TKDD), 2019
  • Federated Learning-NeurIPS, 2019
  • IEEE Transactions on Parallel and Distributed Systems (TPDS), 2018
  • IEEE Transactions on Big Data, 2018
  • PACT, 2019; VLDB demo track, 2018; ICDE demo track, 2019; CIKM, 2018

Program Committee

  • ISC High Performance Conference, AI and ML track, 2020
  • Publicity co-chair, Australasian Database Conference (ADC), 2020.
  • ACM International Conference on Information and Knowledge Management (CIKM), 2019
  • International Symposium on Cyberspace Safety and Security (CSS), 2017

Education/Academic qualification

Computer Science, PhD, University of Melbourne

Software Engineering, Bachelor, South China University of Technology

Keywords

  • Machine Learning Systems
  • Parallel computing
  • GPU Computing
  • Data mining and knowledge discovery

Fingerprint Dive into the research topics where Zeyi Wen is active. These topic labels come from the works of this person. Together they form a unique fingerprint.

Decision trees Engineering & Materials Science
Program processors Engineering & Materials Science
Learning systems Engineering & Materials Science
Computer workstations Engineering & Materials Science
Sorting Engineering & Materials Science
Data mining Engineering & Materials Science
Graphics processing unit Engineering & Materials Science
Data storage equipment Engineering & Materials Science

Network Recent external collaboration on country level. Dive into details by clicking on the dots.

Research Output 2018 2019

  • 7 Citations
  • 1 h-Index
  • 1 Conference paper
  • 1 Special issue

Adaptive Kernel Value Caching for SVM Training

Li, Q., Wen, Z. & He, B., 2019, In : IEEE Transactions on Neural Networks and Learning Systems.

Research output: Contribution to journalSpecial issue

7 Citations (Scopus)

Efficient Gradient Boosted Decision Tree Training on GPUs

Wen, Z., He, B., Ramamohanarao, K., Lu, S. & Shi, J., 2018, IEEE International Parallel and Distributed Processing Symposium (IPDPS). p. 234-243 10 p.

Research output: Chapter in Book/Conference paperConference paper

Decision trees
Program processors
Learning systems
Computer workstations
Sorting