paper-with-me

Papers

Compute Only Once: UG-Separation for Efficient Large Recommendation Models

2026-02-11 · Hui Lu, Zheng Chai, Shipeng Bai, Hao Zhang, Zhifang Fan, Kunmin Bai, Ke Sun, Yingwen Wu, Bingzheng Wei, Xiang Sun, Ziyan Gong, Tianyi Liu, Hua Chen, Deping Xie, Zhongkai Chen, Zhiliang Guo, Qiwei Chen, Yuchao Zheng arxiv

Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behaviors, but this trend also leads to prohibitive training and inference costs. While long-sequence models can reuse user-side computation through KV Caching, such reuse is difficult in TokenMixer-based dense feature interaction architectures, where user and group features are deeply entangled and mixed-up across layers. In this work, we present User-Group Separation (UG-Sep), an industrial large-scale framework that enables user-side computation reusable in TokenMixer-based dense interaction models for the first time. UG-Sep explicitly disentangles user-side and item-side information flows within token-mixing layers, ensuring that a subset of tokens preserves purely user-side representations across layers. This design allows the corresponding per-token computations to be reused across multiple samples, significantly reducing redundant inference cost. To compensate for the potential expressive capacity loss induced by masking, we further propose an Information Compensation strategy that adaptively reconstructs suppressed user-item interactions. Moreover, as UG-Sep substantially reduces user-side FLOPs and exposes memory-bound components, we incorporate W8A16 (8-bit weight, 16-bit activation) weight-only quantization to alleviate memory bandwidth bottlenecks and achieve additional acceleration. We conduct extensive offline evaluations and large-scale online A/B experiments at ByteDance to validate the effectiveness of UG-Sep. Results show that UG-Sep reduces inference latency by up to 20% without causing adverse changes to online user experience and commercial metrics on multiple influential business scenarios compared to TokenMixer at ByteDance, including Douyin Feed Recommendation, Hongguo Feed Recommendation, Chuanshanjia Ads, and Qianchuan Ads.

📄 PDF Abstract BibTeX arXiv:2602.10455

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

NISQ-ready community detection based on separation-node identification

2022-12-30 · Jonas Stein, Dominik Ott, Jonas Nüßlein, David Bucher 외

The analysis of network structure is essential to many scientific areas, ranging from biology to sociology. As the computational task of clustering these networks into partitions, i.e., solving the community detection pr…

Community DetectionSociology

A Recommendation Model Utilizing Separation Embedding and Self-Attention for Feature Mining

2024-10-19 · Wenyi Liu, Rui Wang, Yuanshuai Luo, Jianjun Wei 외

With the explosive growth of Internet data, users are facing the problem of information overload, which makes it a challenge to efficiently obtain the required resources. Recommendation systems have emerged in this conte…

Click-Through Rate Predictionfeature selectionProduct RecommendationRecommendation Systems

An adaptive denoising recommendation algorithm for causal separation bias

2023-11-15 · Conference 2023 11 · Zhangqiuling, Xuhuayang, Wangjianfang

In recommender systems, user selection bias often influences user-item interactions, e.g., users are more likely to rate their previously preferred or popular items. Existing methods can leverage the impact of selection …

Causal InferenceDenoisingMulti-Task LearningRecommendation Systems+1

Blind Source Separation for NMR Spectra with Negative Intensity

2020-02-07 · Ryan J. McCarty, Nimish Ronghe, Mandy Woo, Todd M. Alam

NMR spectral datasets, especially in systems with limited samples, can be difficult to interpret if they contain multiple chemical components (phases, polymorphs, molecules, crystals, glasses, etc...) and the possibility…

Benchmarkingblind source separation

Iconographic Classification and Content-Based Recommendation for Digitized Artworks

2026-02-23 · Krzysztof Kutt, Maciej Baczyński arxiv

We present a proof-of-concept system that automates iconographic classification and content-based recommendation of digitized artworks using the Iconclass vocabulary and selected artificial intelligence methods. The prot…

Object Detection