Yongheng Xu

Yongheng Xu

Auto-generated profile, based on publicly available information

Yongheng Xu

School of Computer and Engineering, Sun Yat-sen University, Guangzhou, 510000, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
7 May 2024 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
GLGuoliang Lin
Guoliang Lin
YXYongheng Xu
Yongheng Xu
HLHanjiang Lai
Hanjiang Lai
JYJian Yin
Jian Yin
Few-shot learning with $N$ -way $K$ -shot scheme is an open challenge in machine learning. Many metric-based approaches have been proposed to tackle this problem, e.g., the Matching Networks and CLIP-Adapter. Despite that these approaches have shown significant progress, the mechanism of why these methods succeed has not been well explored. In this paper, we try to interpret these metric-based few-shot learning methods via causal mechanism. We show that the existing approaches can be viewed as specific forms of front-door adjustment, which can alleviate the effect of spurious correlations and thus learn the causality. This causal interpretation could provide us a new perspective to better understand these existing metric-based methods. Further, based on this causal interpretation, we simply introduce two causal methods for metric-based few-shot learning, which considers not only the relationship between examples but also the diversity of representations. Experimental results demonstrate the superiority of our proposed methods in few-shot classification on various benchmark datasets.

20 February 2026 in Neural Networks
Verified
Journal Article
Closed access
KZKun Zou
Kun Zou
YXYongheng Xu
Yongheng Xu
Jianxing YuJianxing Yu
Jianxing Yu
YPYan Pan
Yan Pan
JYJian Yin
Jian Yin
HLHanjiang Lai
Hanjiang Lai