Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Wendi Li's Homepage
About me
Page not in menu
This is a page not in th emain menu
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
2019 The CCF Elite Collegiate Award
from China Computer Federation
2020 The University Level Excellent Graduation Design
from South China University of Technology
2019 The National Scholarship
from Ministry of Education of China
2020 The Excellent Award in Stars of Tomorrow
from Microsoft Research Asia
publications
HELP: An LSTM-based Approach to Hyperparameter Exploration in Neural Network Learning
Published in Neurocomputing, 2021
Wendi Li, Wing W. Y. Ng, Ting Wang, Marcello Pelillo, Sam Kwong
Paper link: [WEB]
- Focused on a learning-to-learn problem, which aimed to automatically learn the hyperparameters of deep neural networks by using an LSTM-based predictor.
- The proposed LSTM-based predictor not only retains the successful historical examples but also learns from failure lessons, used ablation studies to determine its optimal architecture.
Population-based Hyperparameter Tuning with Multi-task Collaboration
Published in IEEE Transactions on Neural Networks and Learning Systems, 2021
Wendi Li, Ting Wang, Wing W. Y. Ng
- Propose a population-based hyperparameter tuning framework combining multi-task collaboration. For the tasks in the task pool, it can find hyperparameter configurations that work for the current task, which can also be put into use in other tasks after slightly re-tuned.
- The results show significant improvements in generalization abilities yielded by neural networks trained using our method and better performances achieved by the multi-task meta-learning concept.
DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation
Published in AAAI, 2022
Wendi Li, Xiao Yang, Weiqing Liu, Yingce Xia, Jiang Bian
Paper link: [arXiv] [CODE] [POSTER] [REPORT (Chinese)]
- Proposed a meta-learning method DDG-DA for concept drift adaptation. The meta-model learns to guide the retraining process of the base model by sample reweighting and aims to improve the performance of the base model on unseen test data.
- The meta-model improved performance by $11.3\%$ in the signal-based metrics, and $46.7\%$ in the portfolio-based metrics compared to the baseline.
talks
Research on Engine Architecture Design for 3D Scenes based on VR
Published:
Supervisor: Zelin Chen
Deep Network Optimization Method based on Hyperparameter Prediction
Published:
Supervisor: Wing W.Y. Ng
Research on Hyperparameter Tuning with Multi-task Collaboration
Published:
Supervisor: Wing W.Y. Ng
Research on Adjusting the Proportion of Adversarial Samples
Published:
Supervisor: Gerald Friedland
Temporal Light Detection and Ranging Point Cloud Prediction
Published:
Supervisor: Avideh Zakhor
Robust High-Dimensional Image Data Translation via Disentangled Feature Representations
Published:
Supervisor: Yi Ma
Meta-learning-based Data Feeding in Stock Market Prediction
Published:
Supervisor: Xiao Yang
- Developed and maintained the quant platform Qlib, a quantitative-research library for online trading.
- Focused on data feeding in stock market prediction. Proposed a meta-learning-based method to reweight samples. The meta-model learned to guide the retraining process of the base model by sample reweighting and aimed to improve the performance of the base model on unseen test data.
- Designed Meta-Controller, Reweighter frameworks in Qlib, and merged the meta-model into the frameworks.
- Finished an academic paper (page), it is accepted by AAAI 2022.
License Plate Recognition System based on Domain Adaptation
Published:
Supervisor: Mohit Gupta
MD5 Crypt Cracking Algorithm based on GPU-Accelerated CUDA
Published:
Supervisor: Dan Negrut
teaching
aRobot
Android APP, Ver 1.0, 2016
It is a APP, a project of mobile application development. It is made by APP Inventor.
Runner Game
Parkour Game, Ver 1.4, 2017
This is a game made by Unreal Engine 4. It is type of parkour game.
Bomber Man
RPG Game, Ver 1.0, 2018
This is a game made by Unreal Engine 4. It is type of RPG game.