Weighted-Rank Contrastive Regression for Robust Learning on Imbalance Social Media Popularity Prediction

Yen Liang Lai, Yuh-Jzer Joung

Keywords: Social Media Popularity Prediction, Contrastive Learning, Imbalance Regression, Rank-N-Contrast, Social Media Prediction Dataset

Abstract:

Social Media Popularity Prediction (SMPP) is the task of forecasting the level of engagement a social media post will receive. It is crucial for understanding audience engagement and enabling targeted marketing strategies. However, the inherent imbalance in real-world social media data, where certain popularity levels are underrepresented, poses a significant challenge. In this study, we leveraged the recent success of contrastive learning and its growing integration into regression tasks by introducing a Weighted-Rank CR loss to address the data imbalance challenges. Experiments on the Social Media Prediction Dataset demonstrated that our method outperformed the vanilla approach and the current state-of-the-art contrastive regression approach Rank-N-Contrast.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 6798