lykeven
Student at Tsinghua University
Beijing, China
Summary
🤩
Rockstarlykeven is a software engineer and THU master's student in data mining with 11 years of hands-on experience, currently based in Beijing. He contributes to graph deep learning tooling as a back-end developer on the well-regarded CogDL library, debugging models, adding weighted-graph support, tuning defaults, and enabling parallel training. Comfortable delving into model internals and dataset handling, he bridges research-grade algorithms and production-ready engineering. His profile reflects a pragmatic problem-solver who prefers fixing complex bugs and improving performance over flashy features.
11 years of coding experience
Github Skills (8)
pytorch10
deep-learning10
graph-neural-network10
python10
data-structure7
data-structures7
algorithm7
algorithms7
Programming languages (2)
Github contributions (5)
THUDM/CogDL
Jun 2019 - Jul 2020
CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)
Role in this project:
Back-end Developer
Back-end DeveloperContributions:25 commits, 16 pushes, 3 comments in 1 year
Contributions summary:Lykeven primarily fixed errors in the code related to graph deep learning models within the CogDL library. The commits indicate debugging efforts, as well as updates to model parameters and functionality. The user also contributed to adding support for weighted graphs within the datasets and updated the model default parameters. Furthermore, the user added support for parallel training to the core library.
pytorchleaderboardgraph-convolutional-networksgnndeep-learning-on-graphs
lykeven/IDGAN
Jun 2017 - Jan 2018
Contributions:28 pushes, 1 branch in 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.