RAMP: Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways
2026-07-20 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors present RAMP, a method to improve predictions of whether users will click on or buy ads when personalized data like age or gender is not available due to privacy rules. RAMP uses two separate pathways: one for personalized features that can be masked out and one for non-personalized data, plus a technique to align these pathways for better predictions without personal info. They tested RAMP on public and real-world data and found it works better than current methods when personal features are missing, while still doing well when such data is available. This approach helps keep ad recommendations effective while respecting privacy.
click-through rate (CTR)conversion rate (CVR)personalized featuresprivacy constraintsdual-tower modelfeature maskingdistillationprediction alignmentonline advertisingrecommendation systems
Authors
Dairui Liu, Zhongyi Lu, Roger Zhe Li, Changhong Jin, Jitao Lu, Xinyang Shao, Bichen Shi, Mete Sertkan, Aghiles Salah, Aonghus Lawlor, Barry Smyth, Tri Kurniawan Wijaya, Ruihai Dong, Xingsheng Guo
Abstract
Click-through rate (CTR) and conversion rate (CVR) prediction are fundamental tasks in online advertising, aiming to estimate the likelihood of user interactions based on various features. While personalized attributes such as age and gender can significantly enhance predictive accuracy, their use is increasingly restricted by privacy regulations, thereby limiting available data for both training and inference. To address this challenge, we propose RAMP (Robust Ad Recommendation Under Limited Personalized-Feature Availability via Masking and Alignment Pathways), which is designed to improve CTR/CVR prediction accuracy when personalized features are not accessible, thus supporting deployment in privacy-constrained settings.RAMP consists of (i) a personalized pathway built upon a dual-tower component with identical inputs but independent parameters, where output masking separates predictions for personalized and non-personalized signals, (ii) a separate non-personalized pathway trained with non-personalized features only, and (iii) a distillation-inspired prediction-alignment architecture between (i) and (ii) that improves prediction when personalized features are unavailable. We conduct comprehensive experiments using both public benchmarks and industrial datasets to evaluate the performance of RAMP. Our evaluation spans multiple backbone models and different settings: with and without access to personalized features. The results show that RAMP consistently outperforms state-of-the-art methods when personalized features are missing, while maintaining competitive performance when all features are available. %demonstrating its effectiveness and practicality for real-world advertising systems. Our code is publicly available at https://github.com/Ruixinhua/RAMP.