paper-with-me

홈 › Papers

COLD: Towards the Next Generation of Pre-Ranking System

2020-07-31 · Zhe Wang, Liqin Zhao, Biye Jiang, Guorui Zhou, Xiaoqiang Zhu, Kun Gai

Multi-stage cascade architecture exists widely in many industrial systems such as recommender systems and online advertising, which often consists of sequential modules including matching, pre-ranking, ranking, etc. For a long time, it is believed pre-ranking is just a simplified version of the ranking module, considering the larger size of the candidate set to be ranked. Thus, efforts are made mostly on simplifying ranking model to handle the explosion of computing power for online inference. In this paper, we rethink the challenge of the pre-ranking system from an algorithm-system co-design view. Instead of saving computing power with restriction of model architecture which causes loss of model performance, here we design a new pre-ranking system by joint optimization of both the pre-ranking model and the computing power it costs. We name it COLD (Computing power cost-aware Online and Lightweight Deep pre-ranking system). COLD beats SOTA in three folds: (i) an arbitrary deep model with cross features can be applied in COLD under a constraint of controllable computing power cost. (ii) computing power cost is explicitly reduced by applying optimization tricks for inference acceleration. This further brings space for COLD to apply more complex deep models to reach better performance. (iii) COLD model works in an online learning and severing manner, bringing it excellent ability to handle the challenge of the data distribution shift. Meanwhile, the fully online pre-ranking system of COLD provides us with a flexible infrastructure that supports efficient new model developing and online A/B testing.Since 2019, COLD has been deployed in almost all products involving the pre-ranking module in the display advertising system in Alibaba, bringing significant improvements.

📄 PDF Abstract BibTeX arXiv:2007.16122

Code (2)

zsbluesky/COLD tf
zsbluesky/COLD-Towards-the-Next-Generation-of-Pre-Ranking-System tf

Tasks

Recommendation Systems

Similar Papers 제목 키워드 기반

Improving Deep Learning For Airbnb Search

2020-02-10 · Malay Haldar, Mustafa Abdool, Prashant Ramanathan, Tyler Sax 외

The application of deep learning to search ranking was one of the most impactful product improvements at Airbnb. But what comes next after you launch a deep learning model? In this paper we describe the journey beyond, d…

Deep Learning

Order-agnostic Identifier for Large Language Model-based Generative Recommendation

2025-02-15 · Xinyu Lin, Haihan Shi, Wenjie Wang, Fuli Feng 외

Leveraging Large Language Models (LLMs) for generative recommendation has attracted significant research interest, where item tokenization is a critical step. It involves assigning item identifiers for LLMs to encode use…

Collaborative FilteringLanguage ModelingLanguage ModellingLarge Language Model

Diagnosing LLM-based Rerankers in Cold-Start Recommender Systems: Coverage, Exposure and Practical Mitigations

2026-02-09 · Ekaterina Lemdiasova, Nikita Zmanovskii arxiv

Large language models (LLMs) and cross-encoder rerankers have gained attention for improving recommender systems, particularly in cold-start scenarios where user interaction history is limited. However, practical deploym…

Movie Recommendation

Semi-supervised Collaborative Ranking with Push at Top

2015-11-17 · Iman Barjasteh, Rana Forsati, Abdol-Hossein Esfahanian, Hayder Radha

Existing collaborative ranking based recommender systems tend to perform best when there is enough observed ratings for each user and the observation is made completely at random. Under this setting recommender systems c…

Collaborative RankingRecommendation Systems

A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges

2025-07-17 · Rahul Raja, Anshaj Vats, Arpita Vats, Anirban Majumder arxiv

Recommender systems have traditionally followed modular architectures comprising candidate generation, multi-stage ranking, and re-ranking, each trained separately with supervised objectives and hand-engineered features.…