COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems

• URL: http://arxiv.org/abs/2601.02807v1
• Date: Tue, 06 Jan 2026 08:29:12 GMT
• Title: COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems
• Authors: Sohini Roychowdhury, Doris Wang, Qian Ge, Joy Mu, Srihari Reddy,
• Abstract summary: We present a novel framework for enhancing user-ad representations without increasing model inference or serving complexity.<n>The proposed method can boost the area under curve (AUC) and the slope of scaling curves for ad-impression sources by 1.56 to 2 times.
• Score: 2.1182747626493885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diverse and enriched data sources are essential for commercial ads-recommendation models to accurately assess user interest both before and after engagement with content. While extended user-engagement histories can improve the prediction of user interests, it is equally important to embed activity sequences from multiple sources to ensure freshness of user and ad-representations, following scaling law principles. In this paper, we present a novel three-dimensional framework for enhancing user-ad representations without increasing model inference or serving complexity. The first dimension examines the impact of incorporating diverse event sources, the second considers the benefits of longer user histories, and the third focuses on enriching data with additional event attributes and multi-modal embeddings. We assess the return on investment (ROI) of our source enrichment framework by comparing organic user engagement sources, such as content viewing, with ad-impression sources. The proposed method can boost the area under curve (AUC) and the slope of scaling curves for ad-impression sources by 1.56 to 2 times compared to organic usage sources even for short online-sequence lengths of 100 to 10K. Additionally, click-through rate (CTR) prediction improves by 0.56% AUC over the baseline production ad-recommendation system when using enriched ad-impression event sources, leading to improved sequence scaling resolutions for longer and offline user-ad representations.

Related papers

• Generative Recommendation for Large-Scale Advertising [43.694084612630554]
  We present a production-oriented generative recommender co-designed across architecture, learning, and serving.<n> GR4AD has been fully deployed in Kuaishou advertising system with over 400 million users.
  arXiv  Detail & Related papers  (2026-02-26T08:15:26Z)
• Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation [7.070021001906444]
  News recommendation plays a critical role in online news platforms by helping users discover relevant content.<n>Cross-domain news recommendation further requires inferring user's underlying information needs from heterogeneous signals.<n>We present a reinforcement learning framework that trains large language models to generate high-quality lists of interest-driven news search queries.
  arXiv  Detail & Related papers  (2026-02-16T18:45:40Z)
• DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations [5.168870928194366]
  We introduce Dynamix, a scalable, personalized sequence exploration framework for online ad-recommendation systems.<n>Dynamix categorizes users-engagements at session and surface-levels by leveraging correlations between dwell-times and ad-conversion events.<n>We show that Dynamix achieves significant cost efficiency and performance improvements in online user-sequence based recommendation models.
  arXiv  Detail & Related papers  (2025-11-23T08:10:33Z)
• Enhancing Serendipity Recommendation System by Constructing Dynamic User Knowledge Graphs with Large Language Models [0.9262403397108375]
  Large language models (LLMs) have demonstrated potential serendipity in recommendation, thanks to their extensive world knowledge and superior reasoning capabilities.<n>We propose a method that leverages llm to dynamically construct user knowledge graphs, thereby enhancing the serendipity of recommendation systems.
  arXiv  Detail & Related papers  (2025-08-06T02:52:09Z)
• CTR-Driven Advertising Image Generation with Multimodal Large Language Models [53.40005544344148]
  We explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective.<n>To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL)<n>Our method achieves state-of-the-art performance in both online and offline metrics.
  arXiv  Detail & Related papers  (2025-02-05T09:06:02Z)
• GACE: Learning Graph-Based Cross-Page Ads Embedding For Click-Through Rate Prediction [3.3840833400287593]
  This paper proposes a graph-based cross-page ads embedding generation method. It generates representations embedding of cold-start and existing ads across various pages. The results show that our method is significantly superior to the SOTA method.
  arXiv  Detail & Related papers  (2024-01-15T03:12:21Z)
• Deep Context Interest Network for Click-Through Rate Prediction [16.37806484383383]
  We propose a novel model named Deep Context Interest Network (DCIN), which integrally models the click and its display context to learn users' context-aware interests. DCIN has been deployed on our online advertising system serving the main traffic, which brings 1.5% CTR and 1.5% RPM lift.
  arXiv  Detail & Related papers  (2023-08-11T09:32:58Z)
• Feature Decoupling-Recycling Network for Fast Interactive Segmentation [79.22497777645806]
  Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input. We propose the Feature Decoupling-Recycling Network (FDRN), which decouples the modeling components based on their intrinsic discrepancies.
  arXiv  Detail & Related papers  (2023-08-07T12:26:34Z)
• PIE: Personalized Interest Exploration for Large-Scale Recommender Systems [0.0]
  We present a framework for exploration in large-scale recommender systems to address these challenges. Our methodology can be easily integrated into an existing large-scale recommender system with minimal modifications. Our work has been deployed in production on Facebook Watch, a popular video discovery and sharing platform serving billions of users.
  arXiv  Detail & Related papers  (2023-04-13T22:25:09Z)
• Continuous Input Embedding Size Search For Recommender Systems [60.89189829112067]
  Continuous input embedding size search (CIESS) is a novel RL-based method that operates on a continuous search space with arbitrary embedding sizes to choose from.<n> CIESS is also model-agnostic and hence generalizable to a variety of latent factor RSs.<n> experiments on two real-world datasets have shown state-of-the-art performance of CIESS under different memory budgets.
  arXiv  Detail & Related papers  (2023-04-07T06:46:37Z)
• VFed-SSD: Towards Practical Vertical Federated Advertising [53.08038962443853]
  We propose a semi-supervised split distillation framework VFed-SSD to alleviate the two limitations. Specifically, we develop a self-supervised task MatchedPair Detection (MPD) to exploit the vertically partitioned unlabeled data. Our framework provides an efficient federation-enhanced solution for real-time display advertising with minimal deploying cost and significant performance lift.
  arXiv  Detail & Related papers  (2022-05-31T17:45:30Z)
• Contextual Bandits for Advertising Campaigns: A Diffusion-Model Independent Approach (Extended Version) [73.59962178534361]
  We study an influence problem in which little is assumed to be known about the diffusion network or about the model that determines how information may propagate. In this setting, an explore-exploit approach could be used to learn the key underlying diffusion parameters, while running the campaign. We describe and compare two methods of contextual multi-armed bandits, with upper-confidence bounds on the remaining potential of influencers.
  arXiv  Detail & Related papers  (2022-01-13T22:06:10Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.