Rongzhi Zhang

Rongzhi Zhang

Auto-generated profile, based on publicly available information

Rongzhi Zhang

Georgia Institute of Technology, Atlanta, GA, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 January 2022
Verified
Conference Paper
Open access
PDF file
YYYue Yu
Yue Yu
LKLingkai Kong
Lingkai Kong
JZJieyu Zhang
Jieyu Zhang
RZRongzhi Zhang
Rongzhi Zhang
CZChao Zhang
Chao Zhang
Yue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

1 January 2023
Verified
Conference Paper
Open access
PDF file
YYYue Yu
Yue Yu
RZRongzhi Zhang
Rongzhi Zhang
RXRan Xu
Ran Xu
JZJieyu Zhang
Jieyu Zhang
JSJiaming Shen
Jiaming Shen
CZChao Zhang
Chao Zhang
Yue Yu, Rongzhi Zhang, Ran Xu, Jieyu Zhang, Jiaming Shen, Chao Zhang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

4 August 2023
Verified
Conference Paper
Open access
RZRongzhi Zhang
Rongzhi Zhang
YYYue Yu
Yue Yu
JSJiaming Shen
Jiaming Shen
XCXiquan Cui
Xiquan Cui
CZChao Zhang
Chao Zhang
Boosting is a commonly used technique to enhance the performance of a set of base models by combining them into a strong ensemble model. Though widely adopted, boosting is typically used in supervised learning where the data is labeled accurately. However, in weakly supervised learning, where most of the data is labeled through weak and noisy sources, it remains nontrivial to design effective boosting approaches. In this work, we show that the standard implementation of the convex combination of base learners can hardly work due to the presence of noisy labels. Instead, we propose LocalBoost, a novel framework for weakly-supervised boosting. LocalBoost iteratively boosts the ensemble model from two dimensions, i.e., intra-source and inter-source. The intra-source boosting introduces locality to the base learners and enables each base learner to focus on a particular feature regime by training new base learners on granularity-varying error regions. For the inter-source boosting, we leverage a conditional function to indicate the weak source where the sample is more likely to appear. To account for the weak labels, we further design an estimate-then-modify approach to compute the model weights. Experiments on seven datasets show that our method significantly outperforms vanilla boosting methods and other weakly-supervised methods.

1 May 2015 in Optics Communications
Verified
Journal Article
Closed access
SGShiping Guo
Shiping Guo
RZRongzhi Zhang
Rongzhi Zhang
JLJisheng Li
Jisheng Li
JZJianhua Zou
Jianhua Zou
RXRong Xu
Rong Xu
CLChanghai Liu
Changhai Liu

24 August 2024
Verified
Conference Paper
Open access
RZRongzhi Zhang
Rongzhi Zhang
JSJiaming Shen
Jiaming Shen
TLTianqi Liu
Tianqi Liu
JLJialu Liu
Jialu Liu
MBMichael Bendersky
Michael Bendersky
CZChao Zhang
Chao Zhang
Knowledge distillation is a popular technique to transfer knowledge from a large teacher model to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher's output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher's output distribution and the ground truth label distribution. Therefore, forcing the student to blindly imitate the unreliable teacher output distribution leads to inferior performance. To this end, we propose a novel knowledge distillation objective PTLoss by first representing the vanilla KL-based distillation loss function via a Maclaurin series and then perturbing the leading-order terms in this series. This perturbed loss implicitly transforms the original teacher into a proxy teacher with a distribution closer to the ground truth distribution. We establish the theoretical connection between this "distribution closeness'' and the student model generalizability, which enables us to select the PTLoss's perturbation coefficients in a principled way. Extensive experiments on six public benchmark datasets demonstrate the effectiveness of PTLoss with teachers of different scales.