Hadamard product feature interactions work because they make CTR models quadratic networks, and the proposed QNN-alpha with multi-head Khatri-Rao product and self-ensemble loss achieves state-of-the-art results on six public click-through-rate datasets.
Understanding the Ranking Loss for Recommendation with Sparse User Feedback
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Click-through rate (CTR) prediction is a crucial area of research in online advertising. While binary cross entropy (BCE) has been widely used as the optimization objective for treating CTR prediction as a binary classification problem, recent advancements have shown that combining BCE loss with an auxiliary ranking loss can significantly improve performance. However, the full effectiveness of this combination loss is not yet fully understood. In this paper, we uncover a new challenge associated with the BCE loss in scenarios where positive feedback is sparse: the issue of gradient vanishing for negative samples. We introduce a novel perspective on the effectiveness of the auxiliary ranking loss in CTR prediction: it generates larger gradients on negative samples, thereby mitigating the optimization difficulties when using the BCE loss only and resulting in improved classification ability. To validate our perspective, we conduct theoretical analysis and extensive empirical evaluations on public datasets. Additionally, we successfully integrate the ranking loss into Tencent's online advertising system, achieving notable lifts of 0.70% and 1.26% in Gross Merchandise Value (GMV) for two main scenarios. The code is openly accessible at: https://github.com/SkylerLinn/Understanding-the-Ranking-Loss.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.IR 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Revisiting Feature Interactions from the Perspective of Quadratic Neural Networks for Click-through Rate Prediction
Hadamard product feature interactions work because they make CTR models quadratic networks, and the proposed QNN-alpha with multi-head Khatri-Rao product and self-ensemble loss achieves state-of-the-art results on six public click-through-rate datasets.