Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification
Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Li Gao · 2023
Item categorization (IC) aims to classify product descriptions into leaf nodes in a categorical taxonomy, which is a key technology used in a wide range of applications.Along with the fact that most datasets often has a long-tailed distribution, classification performances on tail labels tend to be poor due to scarce supervision, causing many issues in real-life applications.To address IC task's long-tail issue, K-positive contrastive loss (KCL) is proposed on image classification task and can be applied on the IC task when using text-based contrastive learning, e.g., SimCSE.However, one shortcoming of using KCL has been neglected in previous research: false negative (FN) instances may harm the KCL's representation learning.To address the FN issue in the KCL, we proposed to reweight the positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K +1 as close as possible.After controlling FN instances with the proposed method, IC performance has been further improved and is superior to other LT-addressing methods.