mlsanityData to 14 Oct 2026

Large Foundation Model for Ads Recommendation

arXiv 2508.14948 ↗First posted 20 Aug 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Online advertising relies on accurate recommendation models, with recent advances using pre-trained large-scale foundation models (LFMs) to capture users' general interests across multiple scenarios and tasks. However, existing methods have critical limitations: they extract and transfer only user representations (URs), ignoring valuable item representations (IRs) and user-item cross representations (CRs); and they simply use a UR as a feature in downstream applications, which fails to bridge upstream-downstream gaps and overlooks more transfer granularities. In this paper, we propose LFM4Ads, an All-Representation Multi-Granularity transfer framework for ads recommendation. It first comprehensively transfers URs, IRs, and CRs, i.e., all available representations in the pre-trained foundation model. To effectively utilize the CRs, it identifies the optimal extraction layer and aggregates them into transferable coarse-grained forms. Furthermore, we enhance the transferability via multi-granularity mechanisms: non-linear adapters for feature-level transfer, an Isomorphic Interaction Module for module-level transfer, and Standalone Retrieval for model-level transfer. LFM4Ads has been successfully deployed in Tencent's industrial-scale advertising platform, processing tens of billions of daily samples while maintaining terabyte-scale model parameters with billions of sparse embedding keys across approximately two thousand features. Since its production deployment in Q4 2024, LFM4Ads has achieved 10+ successful production launches across various advertising scenarios, including primary ones like Weixin Moments and Channels. These launches achieve an overall GMV lift of 2.45% across the entire platform, translating to estimated annual revenue increases in the hundreds of millions of dollars.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

32 of 56 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Self-Attentive Sequential Recommendationcited by 1,184
  3. 2019BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformercited by 964
  4. 2016Wide & Deep Learning for Recommender Systemscited by 747
  5. 2015Session-based Recommendations with Recurrent Neural Networkscited by 695
  6. 2018Deep Interest Evolution Network for Click-Through Rate Predictioncited by 338
  7. 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 327
  8. 2018xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systemscited by 278
  9. 2017Neural Factorization Machines for Sparse Predictive Analyticscited by 183
  10. 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 177
  11. 2018Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Ratecited by 173
  12. 2019Practice on Long Sequential User Behavior Modeling for Click-Through Rate Predictioncited by 118
20 more
  1. 2019FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Predictioncited by 83
  2. 2023PEPNet: Parameter and Embedding Personalized Network for Infusing with Personalized Prior Informationcited by 60
  3. 2018Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertisingcited by 59
  4. 2022PinnerFormer: Sequence Modeling for User Representation at Pinterestcited by 57
  5. 2023EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commercecited by 49
  6. 2025LONGER: Scaling Up Long Sequence Modeling in Industrial Recommenderscited by 47
  7. 2024eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Datacited by 46
  8. 2018Product-based Neural Networks for User Response Prediction over Multi-field Categorical Datacited by 44
  9. 2021FM2: Field-matrixed Factorization Machines for Recommender Systemscited by 31
  10. 2023On the Embedding Collapse when Scaling up Recommendation Modelscited by 29
  11. 2022ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterestcited by 23
  12. 2019Predicting Different Types of Conversions with Multi-Task Learning in Online Advertisingcited by 21
  13. 2023Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Metacited by 21
  14. 2023STEM: Unleashing the Power of Embeddings for Multi-task Recommendationcited by 19
  15. 2025External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendationcited by 13
  16. 2023Temporal Interest Network for User Response Predictioncited by 9
  17. 2023LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Followingcited by 8
  18. 2024Long-Sequence Recommendation Models Need Decoupled Embeddingscited by 7
  19. 2025Enhancing CTR Prediction with De-correlated Expert Networkscited by 7
  20. 2025Generative Representational Learning of Foundation Models for Recommendationcited by 2

Built on by

Not cited yet.