paper-with-me

홈 › Papers

Item Level Exploration Traffic Allocation in Large-scale Recommendation Systems

2025-05-14 · Dong Wang, Junyi Jiao, Arnab Bhadury, Yaping Zhang, Mingyan Gao

This paper contributes to addressing the item cold start problem in large-scale recommender systems, focusing on how to efficiently gain initial visibility for newly ingested content. We propose an exploration system designed to efficiently allocate impressions to these fresh items. Our approach leverages a learned probabilistic model to predict an item's discoverability, which then informs a scalable and adaptive traffic allocation strategy. This system intelligently distributes exploration budgets, optimizing for the long-term benefit of the recommendation platform. The impact is a demonstrably more efficient cold-start process, leading to a significant increase in the discoverability of new content and ultimately enriching the item corpus available for exploitation, as evidenced by its successful deployment in a large-scale production environment.

📄 PDF Abstract BibTeX arXiv:2505.09033

Code (0)

등록된 구현이 없습니다.

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

Dynamic Prior Thompson Sampling for Cold-Start Exploration in Recommender Systems

2026-02-01 · Zhenyu Zhao, David Zhang, Ellie Zhao, Ehsan Saberian arxiv

Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thomps…

Uniboost: Global Coordination with Value Alignment for Fair and Efficient Traffic Allocation

2026-05-26 · Ge Fan, Nan Zhao, Kai Meng, Cong Luo 외 arxiv

With the rapid evolution of internet services, recommendation systems have become indispensable. In particular, the blending (re-ranking) stage plays a pivotal role in allocating traffic across diverse business objective…

Recommendation Systems

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

2025-09-30 · Ziniu Li, Congliang Chen, Tianyun Yang, Tian Ding 외 arxiv

Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration process is computationally expensive, oft…

Reinforcement LearningMathematical Reasoning

Evolutionary Swarm Robotics: Dynamic Subgoal-Based Path Formation and Task Allocation for Exploration and Navigation in Unknown Environments

2023-12-27 · Lavanya Ratnabala, Robinroy Peter, E. Y. A. Charles

This research paper addresses the challenges of exploration and navigation in unknown environments from an evolutionary swarm robotics perspective. Path formation plays a crucial role in enabling cooperative swarm robots…

AITP: Traffic Accident Responsibility Allocation via Multimodal Large Language Models

2026-04-11 · Zijin Zhou, Songan Zhang arxiv

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in Traffic Accident Detection (TAD) and Traffic Accident Understanding (TAU). However, existing studies mainly focus on describing and interpreti…

Traffic Accident Detection