Le Peng

Le Peng

Auto-generated profile, based on publicly available information

Le Peng

Department of Computer Science and Engineering, University of Minnesota

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 May 2024 in npj Digital Medicine
Verified
Journal Article
Open access
PDF file
LPLe Peng
Le Peng
GLGaoxiang Luo
Gaoxiang Luo
SZSicheng Zhou
Sicheng Zhou
JCJiandong Chen
Jiandong Chen
ZXZiyue Xu
Ziyue Xu
RZRui Zhang
Rui Zhang
Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP). However, the medical field faces challenges in training LMs due to limited data access and privacy constraints imposed by regulations like the Health Insurance Portability and Accountability Act (HIPPA) and the General Data Protection Regulation (GDPR). Federated learning (FL) offers a decentralized solution that enables collaborative learning while ensuring data privacy. In this study, we evaluated FL on 2 biomedical NLP tasks encompassing 8 corpora using 6 LMs. Our results show that: (1) FL models consistently outperformed models trained on individual clients’ data and sometimes performed comparably with models trained with polled data; (2) with the fixed number of total data, FL models training with more clients produced inferior performance but pre-trained transformer-based models exhibited great resilience. (3) FL models significantly outperformed pre-trained LLMs with few-shot prompting.

1 June 2022 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
JSJu Sun
Ju Sun
LPLe Peng
Le Peng
TLTaihui Li
Taihui Li
DADyah Adila
Dyah Adila
ZZZach Zaiman
Zach Zaiman
CTChristopher J. Tignanelli
Christopher J. Tignanelli
This 12-site prospective study characterizes the real-time performance of an artificial intelligence–based diagnostic tool for COVID-19, which may serve as an adjunct to, but not as a replacement f... Purpose To conduct a prospective observational study across 12 U.S. hospitals to evaluate real-time performance of an interpretable artificial intelligence (AI) model to detect COVID-19 on chest ra...

29 November 2022 in medRxiv
Verified
Preprint
Open access
PDF file
LPLe Peng
Le Peng
HLHengyue Liang
Hengyue Liang
GLGaoxiang Luo
Gaoxiang Luo
TLTaihui Li
Taihui Li
JSJu Sun
Ju Sun
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC). However, what levels of features to be reused are problem-dependent, and uniformly finetuning all layers of pretrained models may be suboptimal. This insight has partly motivated the recent differential TL strategies, such as TransFusion (TF) and layer-wise finetuning (LWFT), which treat the layers in the pretrained models differentially. In this paper, we add one more strategy into this family, called TruncatedTL , which reuses and finetunes appropriate bottom layers and directly discards the remaining layers. This yields not only superior MIC performance but also compact models for efficient inference, compared to other differential TL methods. Our code is available at: https://github.com/sun-umn/TTL .

4 June 2023
Verified
Conference Paper
Open access
TLTaihui Li
Taihui Li
HWHengkang Wang
Hengkang Wang
LPLe Peng
Le Peng
XTXian’e Tang
Xian’e Tang
JSJu Sun
Ju Sun
Robust PCA is a standard tool for learning a linear subspace in the presence of sparse corruption or rare outliers. What about robustly learning manifolds that are more realistic models for natural data, such as images? There have been several recent attempts to generalize robust PCA to manifold settings. In this paper, we propose ℓ 1 - and scaling-invariant ℓ 1 /ℓ 2 -robust autoencoders based on a surprisingly compact formulation built on the intuition that deep autoencoders perform manifold learning. We demonstrate on several standard image datasets that the proposed formulation significantly outperforms all previous methods in collectively removing sparse corruption, without clean images for training. Moreover, we also show that the learned manifold structures can be generalized to unseen data samples effectively.

27 November 2023 in medRxiv
Verified
Preprint
Open access
PDF file
LPLe Peng
Le Peng
GLGaoxiang Luo
Gaoxiang Luo
SZSicheng Zhou
Sicheng Zhou
JCJiandong Chen
Jiandong Chen
ZXZiyue Xu
Ziyue Xu
JSJu Sun
Ju Sun
Language models (LMs) such as BERT and GPT have revolutionized natural language processing (NLP). However, the medical field faces challenges in training LMs due to limited data access and privacy constraints imposed by regulations like the Health Insurance Portability and Accountability Act (HIPPA) and the General Data Protection Regulation (GDPR). Federated learning (FL) offers a decentralized solution that enables collaborative learning while ensuring data privacy. In this study, we evaluated FL on 2 biomedical NLP tasks encompassing 8 corpora using 6 LMs. Our results show that: 1) FL models consistently outperformed models trained on individual clients’ data and sometimes performed comparably with models trained with polled data; 2) with the fixed number of total data, FL models training with more clients produced inferior performance but pre-trained transformer-based models exhibited great resilience. 3) FL models significantly outperformed large language models using zero-/one-shot learning and offered lightning inference speed.