World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
34
Citations
6754
World Ranking
11993
National Ranking
4896

Overview

Yingyu Liang is affiliated with the University of Wisconsin-Madison in the United States. Their primary field of study is Computer Science, with a focus that includes several subfields such as Artificial Intelligence, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Materials Chemistry, and Media Technology.

Their research covers a wide range of topics, notably:

  • Adversarial Robustness in Machine Learning
  • Domain Adaptation and Few-Shot Learning
  • Machine Learning and Data Classification
  • Machine Learning and Algorithms
  • Topic Modeling
  • Anomaly Detection Techniques and Applications
  • Natural Language Processing Techniques

Yingyu Liang has a body of published work that includes both conference papers and journal articles. Some recent papers include:

  • Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis, 2020, Proceedings of the AAAI Conference on Artificial Intelligence
  • Learning and generalization in overparameterized neural networks, going beyond two layers, 2025, arXiv (Cornell University)
  • Ultra-short-term power forecast method for the wind farm based on feature selection and temporal convolution network, 2022, ISA Transactions
  • Deep Online Fused Video Stabilization, 2022, 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • Robust Out-of-distribution Detection for Neural Networks, 2020, arXiv (Cornell University)

Their most frequent publication venues are:

  • arXiv (Cornell University), with 50 publications
  • International Journal of Pattern Recognition and Artificial Intelligence, with 4 publications
  • Proceedings of the AAAI Conference on Artificial Intelligence, with 1 publication
  • ISA Transactions, with 1 publication
  • Computational Materials Science, with 1 publication

Yingyu Liang collaborates regularly with several coauthors. Frequent coauthors include:

  • Zhenmei Shi, with 30 joint publications
  • Zhao Song, with 13 joint publications
  • Somesh Jha, with 11 joint publications
  • Xi Wu, with 10 joint publications
  • Jiefeng Chen, with 9 joint publications

Best Publications

  • A Simple but Tough-to-Beat Baseline for Sentence Embeddings

    Sanjeev Arora;Yingyu Liang;Tengyu Ma

  • Generalization and Equilibrium in Generative Adversarial Nets (GANs)

    Sanjeev Arora;Rong Ge;Yingyu Liang;Tengyu Ma

  • Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers

    Zeyuan Allen-Zhu;Yuanzhi Li;Yingyu Liang

  • Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data

    Yuanzhi Li;Yingyu Liang

  • A Latent Variable Model Approach to PMI-based Word Embeddings

    Sanjeev Arora;Yuanzhi Li;Yingyu Liang;Tengyu Ma

  • Learning Relationships between Text, Audio, and Video via Deep Canonical Correlation for Multimodal Language Analysis

    Zhongkai Sun;Prathusha Kameswara Sarma;William A. Sethares;Yingyu Liang

  • Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

    Minyi Dai;Mehmet F. Demirel;Yingyu Liang;Jia-Mian Hu

  • Linear Algebraic Structure of Word Senses, with Applications to Polysemy

    Sanjeev Arora;Yuanzhi Li;Yingyu Liang;Tengyu Ma

  • Scalable Kernel Methods via Doubly Stochastic Gradients

    Bo Dai;Bo Xie;Niao He;Yingyu Liang

  • Robust hierarchical clustering

    Maria-Florina Balcan;Yingyu Liang;Pramod Gupta

  • Clustering under Perturbation Resilience

    Maria Florina Balcan;Yingyu Liang

  • Loss-Balanced Task Weighting to Reduce Negative Transfer in Multi-Task Learning

    Shengchao Liu;Yingyu Liang;Anthony Gitter

  • A la carte embedding: Cheap but effective induction of semantic feature vectors

    Mikhail Khodak;Nikunj Saunshi;Yingyu Liang;Tengyu Ma

  • Improved Distributed Principal Component Analysis

    Maria-Florina Balcan;Vandana Kanchanapally;Yingyu Liang;David Woodruff

  • Diverse Neural Network Learns True Target Functions

    Bo Xie;Yingyu Liang;Le Song

  • N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules

    Shengchao Liu;Mehmet Furkan Demirel;Yingyu Liang

  • Influence Function Learning in Information Diffusion Networks

    Nan Du;Yingyu Liang;Maria Balcan;Le Song

  • Distributed k-means and k-median Clustering on General Topologies

    Maria-Florina F Balcan;Steven Ehrlich;Yingyu Liang

  • Improved Distributed Principal Component Analysis

    Yingyu Liang;Maria-Florina F Balcan;Vandana Kanchanapally;David Woodruff

  • Mapping between fMRI responses to movies and their natural language annotations.

    Kiran Vodrahalli;Po Hsuan Chen;Yingyu Liang;Christopher Baldassano

  • ATOM: Robustifying Out-of-Distribution Detection Using Outlier Mining

    Jiefeng Chen;Yixuan Li;Xi Wu;Yingyu Liang

  • Can Adversarial Weight Perturbations Inject Neural Backdoors

    Siddhant Garg;Adarsh Kumar;Vibhor Goel;Yingyu Liang

Frequent Co-Authors

Maria-Florina Balcan
Maria-Florina Balcan Carnegie Mellon University
Yuanzhi Li
Yuanzhi Li Carnegie Mellon University
Le Song
Le Song Mohamed bin Zayed University of Artificial Intelligence
Sanjeev Arora
Sanjeev Arora Princeton University
Somesh Jha
Somesh Jha University of Wisconsin–Madison
Tengyu Ma
Tengyu Ma Stanford University
David P. Woodruff
David P. Woodruff Carnegie Mellon University
William A. Sethares
William A. Sethares University of Wisconsin–Madison
Nan Du
Nan Du Tencent (China)
Bo Zhang
Bo Zhang Tsinghua University

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Studying Computer Science unlocks a range of related degree options and professional pathways. For those interested in rapid, flexible education, a 1 year computer science degree online program can provide accelerated entry to the field. Such programs are ideal for career changers or those looking to quickly advance their tech skills.

Beyond computer science, related disciplines like environmental science and engineering also offer abundant opportunities. Exploring what can you do with an environmental science major can help you discover interdisciplinary roles that blend technology and sustainability.

If you're interested in engineering, consider affordable digital pathways such as environmental engineering degrees online or the cheapest online mechanical engineering degree options. These online programs make it easier to gain specialized skills while maintaining flexibility.

Whichever pathway you choose, online degrees provide accessible ways to start or advance a STEM career and broaden your professional horizons.

Best Scientists Citing Yingyu Liang

Trending Scientists

Recently Published Articles