Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2502.17494

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

Mingfu Liang·Xi Liu·Rong Jin·Boyang Liu·Qiuling Suo·Qinghai Zhou·Song Zhou·Laming Chen·Hua Zheng·Zhiyuan Li·Shali Jiang·Jiyan Yang·Xiaozhen Xia·Fan Yang·Yasmine Badr·Ellie Wen·Shuyu Xu·Hansey Chen·Zhengyu Zhang·Jade Nie·Chunzhi Yang·Zhichen Zeng·Weilin Zhang·Xingliang Huang·Qianru Li·Shiquan Wang·Evelyn Lyu·Wenjing Lu·Rui Zhang·Wenjun Wang·Jason Rudy·Mengyue Hang·Kai Wang·Yinbin Ma·Shuaiwen Wang·Sihan Zeng·Tongyi Tang·Xiaohan Wei·Longhao Jin·Jamey Zhang·Marcus Chen·Jiayi Xu·Angie Huang·Xihuan Zeng·Chi Zhang·Zhengli Zhao·Jared Yang·Qiang Jin·Xian Chen·Amit Anand Amlesahwaram·Lexi Song·Liang Luo·Yuchen Hao·Nan Xiao·Yavuz Yetim·Luoshang Pan·Gaoxiang Liu·Yuxi Hu·Yuzhen Huang·Jackie Xu·Rich Zhu·Xin Zhang·Yiqun Liu·Hang Yin·Yuxin Chen·Buyun Zhang·Xiaoyi Liu·Xingyuan Wang·Wenguang Mao·Zhijing Li·Zhehui Zhou·Feifan Gu·Qin Huang·Chonglin Sun·Nancy Yu·Shuo Gu·Shupin Mao·Benjamin Au·Jingzheng Qin·Peggy Yao·Jae-Woo Choi·Bin Gao·Ernest Wang·Lei Zhang·Wen-Yen Chen·Ted Lee·Yujie Zha·Yi Meng·Alex Gong·Edison Gao·Jack Hsueh·Jie Zheng·Alireza Vahdatpour·Yiping Han·Yantao Yao·Toshinari Kureha·Shuo Chang·Musharaf Sultan·John Bocharov·Sagar Chordia
View original source ↗Read source document ↗Export metadata ↓

Abstract

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.

Explore related subjects

cs.IRcs.AIcs.LG

Keep this discovery

BibTeXRIS

Mingfu Liang, Xi Liu, Rong Jin, Boyang Liu, Qiuling Suo, Qinghai Zhou, Song Zhou, Laming Chen, Hua Zheng, Zhiyuan Li, Shali Jiang, Jiyan Yang, Xiaozhen Xia, Fan Yang, Yasmine Badr, Ellie Wen, Shuyu Xu, Hansey Chen, Zhengyu Zhang, Jade Nie, Chunzhi Yang, Zhichen Zeng, Weilin Zhang, Xingliang Huang, Qianru Li, Shiquan Wang, Evelyn Lyu, Wenjing Lu, Rui Zhang, Wenjun Wang, Jason Rudy, Mengyue Hang, Kai Wang, Yinbin Ma, Shuaiwen Wang, Sihan Zeng, Tongyi Tang, Xiaohan Wei, Longhao Jin, Jamey Zhang, Marcus Chen, Jiayi Xu, Angie Huang, Xihuan Zeng, Chi Zhang, Zhengli Zhao, Jared Yang, Qiang Jin, Xian Chen, Amit Anand Amlesahwaram, Lexi Song, Liang Luo, Yuchen Hao, Nan Xiao, Yavuz Yetim, Luoshang Pan, Gaoxiang Liu, Yuxi Hu, Yuzhen Huang, Jackie Xu, Rich Zhu, Xin Zhang, Yiqun Liu, Hang Yin, Yuxin Chen, Buyun Zhang, Xiaoyi Liu, Xingyuan Wang, Wenguang Mao, Zhijing Li, Zhehui Zhou, Feifan Gu, Qin Huang, Chonglin Sun, Nancy Yu, Shuo Gu, Shupin Mao, Benjamin Au, Jingzheng Qin, Peggy Yao, Jae-Woo Choi, Bin Gao, Ernest Wang, Lei Zhang, Wen-Yen Chen, Ted Lee, Yujie Zha, Yi Meng, Alex Gong, Edison Gao, Jack Hsueh, Jie Zheng, Alireza Vahdatpour, Yiping Han, Yantao Yao, Toshinari Kureha, Shuo Chang, Musharaf Sultan, John Bocharov, Sagar Chordia. 2025-02-20. External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation. https://arxiv.org/abs/2502.17494

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems use cascaded stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately can create cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, and independently tuned downstream fusion can offset upstream improvements. Existing multi-task fusion methods focus on multi-objective fusion within the ranking stage, and cross-stage methods typically only add a downstream score factor to upstream ranking. Joint optimization of fusion modules across both stages remains largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings and are trained in a single computation graph, so gradients from either stage propagate through the shared representation and influence the other. Second, we introduce a dual-axis preference alignment objective: a vertical cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score, and a horizontal compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence. Third, we find that unconstrained end-to-end fusion optimization can exploit imbalances in item attribute distributions, over-concentrating on high-reward regions at the cost of other objectives. We therefore add an attribute group-relative regularization that computes advantages within attribute groups and normalizes the policy over the same groups, so uniformly promoting an entire high-reward group yields no optimization gain. Offline, UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines. Online A/B tests show a 0.616\% gain in app usage duration. UniRec is fully deployed on the Kuaishou platform.

cs.IR↗
arXiv2026

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

cs.IR↗
arXiv2026

TimelyRAG: Semantic-Temporal Hybrid Retrieval for Time-Critical Question Answering in Overlapping-Evolving Documents

Although large language models (LLMs) and retrieval-augmented generation (RAG) have advanced open-domain question answering (QA), they remain unreliable when documents evolve through amendments. Existing time-sensitive retrieval methods address only the disjoint-evolving environment, where each update is an independent snapshot. However, laws, policies, and regulations often operate in overlapping-evolving environments, where amendments override earlier clauses while preserving most content, creating strong semantic overlap across versions. We propose TimelyRAG, a retriever-agnostic framework that incorporates temporal distance into ranking to align queries with version-appropriate documents. We also introduce TimelyQABench, the first benchmark for regulation-heavy domains with overlapping-evolving challenges. Experiments show consistent gains, up to +28.6% in nDCG@10, highlighting the importance of temporal reasoning for reliable QA over evolving documents. All resources are available at https://github.com/kaist-dmlab/TimelyRAG.

cs.IR↗