paper-with-me

홈 › Papers

Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time

2017-11-21 · Chantat Eksombatchai, Pranav Jindal, Jerry Zitao Liu, Yuchen Liu, Rahul Sharma, Charles Sugnet, Mark Ulrich, Jure Leskovec

User experience in modern content discovery applications critically depends on high-quality personalized recommendations. However, building systems that provide such recommendations presents a major challenge due to a massive pool of items, a large number of users, and requirements for recommendations to be responsive to user actions and generated on demand in real-time. Here we present Pixie, a scalable graph-based real-time recommender system that we developed and deployed at Pinterest. Given a set of user-specific pins as a query, Pixie selects in real-time from billions of possible pins those that are most related to the query. To generate recommendations, we develop Pixie Random Walk algorithm that utilizes the Pinterest object graph of 3 billion nodes and 17 billion edges. Experiments show that recommendations provided by Pixie lead up to 50% higher user engagement when compared to the previous Hadoop-based production system. Furthermore, we develop a graph pruning strategy at that leads to an additional 58% improvement in recommendations. Last, we discuss system aspects of Pixie, where a single server executes 1,200 recommendation requests per second with 60 millisecond latency. Today, systems backed by Pixie contribute to more than 80% of all user engagement on Pinterest.

📄 PDF Abstract BibTeX arXiv:1711.07601

Code (1)

jd557/pixie-rust

Tasks

Recommendation Systems

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Top-K Off-Policy Correction for a REINFORCE Recommender System

2018-12-06 · Minmin Chen, Alex Beutel, Paul Covington, Sagar Jain 외

Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user st…

Recommendation Systems

Large Language Model Simulator for Cold-Start Recommendation

2024-02-14 · Feiran Huang, Yuanchen Bei, Zhenghang Yang, Junyi Jiang 외

Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely solely on content features, limiting their …

Collaborative FilteringLanguage ModelingLanguage ModellingLarge Language Model+2

Scalable Realistic Recommendation Datasets through Fractal Expansions

2019-01-23 · Francois Belletti, Karthik Lakshmanan, Walid Krichene, Yi-fan Chen 외

Recommender System research suffers currently from a disconnect between the size of academic data sets and the scale of industrial production systems. In order to bridge that gap we propose to generate more massive user/…

Recommendation Systems

POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion

2019-05-06 · Wen Chen, Pipei Huang, Jiaming Xu, Xin Guo 외

Increasing demand for fashion recommendation raises a lot of challenges for online shopping platforms and fashion communities. In particular, there exist two requirements for fashion outfit recommendation: the Compatibil…

Feedback Reciprocal Graph Collaborative Filtering

2024-08-05 · Weijun Chen, Yuanchen Bei, Qijie Shen, Hao Chen 외

Collaborative filtering on user-item interaction graphs has achieved success in the industrial recommendation. However, recommending users' truly fascinated items poses a seesaw dilemma for collaborative filtering models…

Collaborative FilteringContrastive LearningRecommendation Systems