# External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation

arXiv: https://arxiv.org/abs/2502.17494 · HTML: https://mlsanity.com/paper/2502.17494/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Builds on (most cited first, 28 of 28)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://mlsanity.com/paper/1703.04247/) (2017)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [Deep & Cross Network for Ad Click Predictions](https://mlsanity.com/paper/1708.05123/) (2017)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems](https://mlsanity.com/paper/2008.13535/) (2020)
- [Wukong: Towards a Scaling Law for Large-Scale Recommendation](https://mlsanity.com/paper/2403.02545/) (2024)
- [Collaborative Large Language Model for Recommender Systems](https://mlsanity.com/paper/2311.01343/) (2023)
- [Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System](https://mlsanity.com/paper/1809.07428/) (2018)
- [BARS: Towards Open Benchmarking for Recommender Systems](https://mlsanity.com/paper/2205.09626/) (2022)
- [Open Benchmarking for Click-Through Rate Prediction](https://mlsanity.com/paper/2009.05794/) (2020)
- [Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks](https://mlsanity.com/paper/1802.06093/) (2018)
- [On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models](https://mlsanity.com/paper/2209.05310/) (2022)
- [FM2: Field-matrixed Factorization Machines for Recommender Systems](https://mlsanity.com/paper/2102.12994/) (2021)
- [Scaling Laws For Dense Retrieval](https://mlsanity.com/paper/2403.18684/) (2024)
- [Scaling Law for Recommendation Models: Towards General-purpose User Representations](https://mlsanity.com/paper/2111.11294/) (2021)
- [Bidirectional Distillation for Top-K Recommender System](https://mlsanity.com/paper/2106.02870/) (2021)
- [Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta](https://mlsanity.com/paper/2311.09544/) (2023)
- [Ensemble Knowledge Distillation for CTR Prediction](https://mlsanity.com/paper/2011.04106/) (2020)
- [Distillation from Heterogeneous Models for Top-K Recommendation](https://mlsanity.com/paper/2303.01130/) (2023)
- [Ads Recommendation in a Collapsed and Entangled World](https://mlsanity.com/paper/2403.00793/) (2024)
- [Unbiased Knowledge Distillation for Recommendation](https://mlsanity.com/paper/2211.14729/) (2022)
- [Continual Collaborative Distillation for Recommender System](https://mlsanity.com/paper/2405.19046/) (2024)

## Built on by (most cited first, 13 of 13)

- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [GR2: Generative Reasoning Re-ranker](https://mlsanity.com/paper/2602.07774/) (2026)
- [Hierarchical LoRA MoE for Efficient CTR Model Scaling](https://mlsanity.com/paper/2510.10432/) (2025)
- [PinFM: Foundation Model for User Activity Sequences at a Billion-scale Visual Discovery Platform](https://mlsanity.com/paper/2507.12704/) (2025)
- [Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment](https://mlsanity.com/paper/2508.02929/) (2025)
- [Two-dimensional Sparse Parallelism for Large Scale Deep Learning Recommendation Model Training](https://mlsanity.com/paper/2508.03854/) (2025)
- [SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling](https://mlsanity.com/paper/2604.12110/) (2026)
- [LoKA: Low-precision Kernel Applications for Recommendation Models At Scale](https://mlsanity.com/paper/2605.10886/) (2026)
- [Large Foundation Model for Ads Recommendation](https://mlsanity.com/paper/2508.14948/) (2025)
- [LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for Recommendation](https://mlsanity.com/paper/2605.29280/) (2026)
- [GR2 Technical Report](https://mlsanity.com/paper/2606.31984/) (2026)
- [Building a User Foundation Model for the Open Web](https://mlsanity.com/paper/2607.28019/) (2026)
- [Progressive Alignment of Recommender Foundation Model through Multi-Phase Post-Training](https://mlsanity.com/paper/2608.06792/) (2026)

## Abstract (arXiv)

Ads recommendation is a prominent service of online advertising systems and has been actively studied. Recent studies indicate that scaling-up and advanced design of the recommendation model can bring significant performance improvement. However, with a larger model scale, such prior studies have a significantly increasing gap from industry as they often neglect two fundamental challenges in industrial-scale applications. First, training and inference budgets are restricted for the model to be served, exceeding which may incur latency and impair user experience. Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system. We propose the External Large Foundation Model (ExFM) framework to address the overlooked challenges. Specifically, we develop external distillation and a data augmentation system (DAS) to control the computational cost of training/inference while maintaining high performance. We design the teacher in a way like a foundation model (FM) that can serve multiple students as vertical models (VMs) to amortize its building cost. We propose Auxiliary Head and Student Adapter to mitigate the data distribution gap between FM and VMs caused by the streaming data issue. Comprehensive experiments on internal industrial-scale applications and public datasets demonstrate significant performance gain by ExFM.