Shan Yang

Dr. Shan Yang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
SLSiyi Liu
Siyi Liu
YLYang Li
Yang Li
JLJiang Li
Jiang Li
SYShan Yang
Shan Yang
YLYunshi Lan
Yunshi Lan
Siyi Liu, Yang Li, Jiang Li, Shan Yang, Yunshi Lan. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.

2 August 2023 in Electronics
Verified
Journal Article
Open access
PDF file
SYShan Yang
Shan Yang
YZYongfei Zhang
Yongfei Zhang
QZQinghua Zhao
Qinghua Zhao
YPYanglin Pu
Yanglin Pu
HYHangyuan Yang
Hangyuan Yang
Deep metric learning aims to learn a mapping function that projects input data into a high-dimensional embedding space, facilitating the clustering of similar data points while ensuring dissimilar ones are far apart. The most recent studies focus on designing a batch sampler and mining online triplets to achieve this purpose. Conventionally, hard negative mining schemes serve as the preferred batch sampler. However, most hard negative mining schemes search for hard examples in randomly selected mini-batches at each epoch, which often results in less-optimal hard examples and thus sub-optimal performances. Furthermore, Triplet Loss is commonly adopted to perform online triplet mining by pulling the hard positives close to and pushing the negatives away from the anchor. However, when the anchor in a triplet is an outlier, the positive example will be pulled away from the centroid of the cluster, thus resulting in a loose cluster and inferior performance. To address the above challenges, we propose the Prototype-based Support Example Miner (pSEM) and Triplet Loss (pTriplet Loss). First, we present a support example miner designed to mine the support classes on the prototype-based nearest neighbor graph of classes. Following this, we locate the support examples by searching for instances at the intersection between clusters of these support classes. Second, we develop a variant of Triplet Loss, referred to as a Prototype-based Triplet Loss. In our approach, a dynamically updated prototype is used to rectify outlier anchors, thus reducing their detrimental effects and facilitating a more robust formulation for Triplet Loss. Extensive experiments on typical Computer Vision (CV) and Natural Language Processing (NLP) tasks, namely person re-identification and few-shot relation extraction, demonstrated the effectiveness and generalizability of the proposed scheme, which consistently outperforms the state-of-the-art models.

1 August 2024
Verified
Book Chapter
Closed access
PDF file
SYShan Yang
Shan Yang
HYHangyuan Yang
Hangyuan Yang
YPYanglin Pu
Yanglin Pu
YWYanbing Wang
Yanbing Wang
ZYZhu-Hong You
Zhu-Hong You


1 January 2025
Verified
Conference Paper
Open access
PDF file
SYShan Yang
Shan Yang
KWKun Wu
Kun Wu
ZLZeju Li
Zeju Li
LZLinlin Zhang
Linlin Zhang
XPXiangyu Pei
Xiangyu Pei
YLYu Liu
Yu Liu
Shan Yang, Kun Wu, Zeju Li, Linlin Zhang, Xiangyu Pei, Leike An, Yu Liu. Findings of the Association for Computational Linguistics: EMNLP 2025. 2025.