Junzhuo Liu

Mr. Junzhuo Liu


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
1 January 2024
Verified
Conference Paper
Open access
PDF file
JLJunzhuo Liu
Junzhuo Liu
XYXuzheng Yang
Xuzheng Yang
WLWeiwei Li
Weiwei Li
PWPeng Wang
Peng Wang
Junzhuo Liu, Xuzheng Yang, Weiwei Li, Peng Wang. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

28 December 2025 in arXiv
Verified
Preprint
Open access
PDF file
WLWeiwei Li
Weiwei Li
JLJunzhuo Liu
Junzhuo Liu
YRYuanyuan Ren
Yuanyuan Ren
YZYuchen Zheng
Yuchen Zheng
YLYahao Liu
Yahao Liu
WLWen Li
Wen Li
Deep learning models are known to often learn features that spuriously correlate with the class label during training but are irrelevant to the prediction task. Existing methods typically address this issue by annotating potential spurious attributes, or filtering spurious features based on some empirical assumptions (e.g., simplicity of bias). However, these methods may yield unsatisfactory performance due to the intricate and elusive nature of spurious correlations in real-world data. In this paper, we propose a data-oriented approach to mitigate the spurious correlation in deep learning models. We observe that samples that are influenced by spurious features tend to exhibit a dispersed distribution in the learned feature space. This allows us to identify the presence of spurious features. Subsequently, we obtain a bias-invariant representation by neutralizing the spurious features based on a simple grouping strategy. Then, we learn a feature transformation to eliminate the spurious features by aligning with this bias-invariant representation. Finally, we update the classifier by incorporating the learned feature transformation and obtain an unbiased model. By integrating the aforementioned identifying, neutralizing, eliminating and updating procedures, we build an effective pipeline for mitigating spurious correlation. Experiments on image and NLP debiasing benchmarks show an improvement in worst group accuracy of more than 20% compared to standard empirical risk minimization (ERM). Codes and checkpoints are available at https://github.com/davelee-uestc/nsf_debiasing .