Yingyu Liang

Yingyu Liang

University of Wisconsin-Madison

H-index: 36

North America-United States

About Yingyu Liang

Yingyu Liang, With an exceptional h-index of 36 and a recent h-index of 32 (since 2020), a distinguished researcher at University of Wisconsin-Madison, specializes in the field of machine learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Provable guarantees for neural networks via gradient feature learning

Fourier Circuits in Neural Networks: Unlocking the Potential of Large Language Models in Mathematical Reasoning and Modular Arithmetic

Domain generalization via nuclear norm regularization

Graph neural network for predicting the effective properties of polycrystalline materials: A comprehensive analysis

When and how does known class help discover unknown ones? provable understanding through spectral analysis

Stratified adversarial robustness with rejection

Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection

Yingyu Liang Information

University

Position

___

Citations(all)

7835

Citations(since 2020)

6416

Cited By

4092

hIndex(all)

36

hIndex(since 2020)

32

i10Index(all)

54

i10Index(since 2020)

46

Email

University Profile Page

Google Scholar

Yingyu Liang Skills & Research Interests

machine learning

Top articles of Yingyu Liang

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

arXiv preprint arXiv:2402.15017

2024/2/22

Provable guarantees for neural networks via gradient feature learning

Advances in Neural Information Processing Systems

2024/2/13

Yingyu Liang
Yingyu Liang

H-Index: 25

Fourier Circuits in Neural Networks: Unlocking the Potential of Large Language Models in Mathematical Reasoning and Modular Arithmetic

arXiv preprint arXiv:2402.09469

2024/2/12

Domain generalization via nuclear norm regularization

2024/1/8

Graph neural network for predicting the effective properties of polycrystalline materials: A comprehensive analysis

Computational Materials Science

2023/10/25

Yingyu Liang
Yingyu Liang

H-Index: 25

Jia-Mian Hu
Jia-Mian Hu

H-Index: 25

When and how does known class help discover unknown ones? provable understanding through spectral analysis

arXiv preprint arXiv:2308.05017

2023/8/9

Stratified adversarial robustness with rejection

2023

Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection

arXiv preprint arXiv:2305.17528

2023/5/27

The trade-off between universality and label efficiency of representations from contrastive learning

2023

Improving foundation models for few-shot learning via multitask finetuning

2023/2/8

Yin Li
Yin Li

H-Index: 12

Yingyu Liang
Yingyu Liang

H-Index: 25

The Trade-off between Label Efficiency and Universality of Representations from Contrastive Learning

2022

A theoretical analysis on feature learning in neural networks: Emergence from inputs and advantage over fixed features

arXiv preprint arXiv:2206.01717

2022/6/3

Yingyu Liang
Yingyu Liang

H-Index: 25

Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials (vol 7, 103, 2021)

npj Computational Materials

2021/7/9

Yingyu Liang
Yingyu Liang

H-Index: 25

Jia-Mian Hu
Jia-Mian Hu

H-Index: 25

Attentive walk-aggregating graph neural networks

Transactions on Machine Learning Research

2022/4/27

Yingyu Liang
Yingyu Liang

H-Index: 25

On the identifiability of mixtures of ranking models

arXiv preprint arXiv:2201.13132

2022/1/31

Xiaomin Zhang
Xiaomin Zhang

H-Index: 4

Yingyu Liang
Yingyu Liang

H-Index: 25

Author Correction: Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials

NPJ Computational Materials

2022

Yingyu Liang
Yingyu Liang

H-Index: 25

Jia-Mian Hu
Jia-Mian Hu

H-Index: 25

Deep online fused video stabilization

2022

Yingyu Liang
Yingyu Liang

H-Index: 25

Best of Both Worlds: Towards Adversarial Robustness with Transduction and Rejection

2022/11/18

Domain generalization with nuclear norm regularization

2022/10/21

Detecting errors and estimating accuracy on unlabeled data with self-training ensembles

Advances in Neural Information Processing Systems

2021/12/6

See List of Professors in Yingyu Liang University(University of Wisconsin-Madison)

Co-Authors

academic-engine