Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tan, Bin, Ge, Wangyao, Wang, Yidi, Liu, Xin, Burtoft, Jeff, Fan, Hao, Wang, Hui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.18166
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908523891261440
author Tan, Bin
Ge, Wangyao
Wang, Yidi
Liu, Xin
Burtoft, Jeff
Fan, Hao
Wang, Hui
author_facet Tan, Bin
Ge, Wangyao
Wang, Yidi
Liu, Xin
Burtoft, Jeff
Fan, Hao
Wang, Hui
contents Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization. We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR prediction. PCR-CA first extracts compact multimodal embeddings from app text, then introduces a Parallel Codebook VQ-AE module that learns discrete semantic representations across multiple codebooks in parallel -- unlike hierarchical residual quantization (RQ-VAE). This design enables independent encoding of diverse aspects (e.g., gameplay, art style), better modeling multiple-category semantics. To bridge semantic and collaborative signals, we employ a contrastive alignment loss at both the user and item levels, enhancing representation learning for long-tail items. Additionally, a dual-attention fusion mechanism combines ID-based and semantic features to capture user interests, especially for long-tail apps. Experiments on a large-scale dataset show PCR-CA achieves a +0.76% AUC improvement over strong baselines, with +2.15% AUC gains for long-tail apps. Online A/B testing further validates our approach, showing a +10.52% lift in CTR and a +16.30% improvement in CVR, demonstrating PCR-CA's effectiveness in real-world deployment. The new framework has now been fully deployed on the Microsoft Store.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18166
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation
Tan, Bin
Ge, Wangyao
Wang, Yidi
Liu, Xin
Burtoft, Jeff
Fan, Hao
Wang, Hui
Information Retrieval
Machine Learning
Modern app store recommender systems struggle with multiple-category apps, as traditional taxonomies fail to capture overlapping semantics, leading to suboptimal personalization. We propose PCR-CA (Parallel Codebook Representations with Contrastive Alignment), an end-to-end framework for improved CTR prediction. PCR-CA first extracts compact multimodal embeddings from app text, then introduces a Parallel Codebook VQ-AE module that learns discrete semantic representations across multiple codebooks in parallel -- unlike hierarchical residual quantization (RQ-VAE). This design enables independent encoding of diverse aspects (e.g., gameplay, art style), better modeling multiple-category semantics. To bridge semantic and collaborative signals, we employ a contrastive alignment loss at both the user and item levels, enhancing representation learning for long-tail items. Additionally, a dual-attention fusion mechanism combines ID-based and semantic features to capture user interests, especially for long-tail apps. Experiments on a large-scale dataset show PCR-CA achieves a +0.76% AUC improvement over strong baselines, with +2.15% AUC gains for long-tail apps. Online A/B testing further validates our approach, showing a +10.52% lift in CTR and a +16.30% improvement in CVR, demonstrating PCR-CA's effectiveness in real-world deployment. The new framework has now been fully deployed on the Microsoft Store.
title PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2508.18166