English
Related papers

Related papers: Mixed-Precision Embeddings for Large-Scale Recomme…

200 papers

Recent recommender systems increasingly leverage embeddings from large pre-trained language models (PLMs). However, such embeddings exhibit two key limitations: (1) PLMs are not explicitly optimized to produce structured and discriminative…

Computation and Language · Computer Science 2026-01-19 Guy Hadad , Neomi Rabaev , Bracha Shapira

Feature embeddings are one of the most essential steps when training deep learning based Click-Through Rate prediction models, which map high-dimensional sparse features to dense embedding vectors. Classic human-crafted embedding size…

Information Retrieval · Computer Science 2022-08-18 Tesi Xiao , Xia Xiao , Ming Chen , Youlong Chen

The Mixture of Experts (MoE) architecture is an important method for scaling Large Language Models (LLMs). It increases model capacity while keeping computation cost low. However, the ultra-large MoE models still have hundreds of billions…

Artificial Intelligence · Computer Science 2025-10-01 Yixiao Chen , Yanyue Xie , Ruining Yang , Wei Jiang , Wei Wang , Yong He , Yue Chen , Pu Zhao , Yanzhi Wang

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Computation and Language · Computer Science 2015-08-04 Jian Tang , Meng Qu , Qiaozhu Mei

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 context. By filtering…

Information Retrieval · Computer Science 2024-10-22 Wenyi Liu , Rui Wang , Yuanshuai Luo , Jianjun Wei , Zihao Zhao , Junming Huang

The Mixture-of-Experts (MoE) architecture has become a predominant paradigm for scaling large language models (LLMs). Despite offering strong performance and computational efficiency, large MoE-based LLMs like DeepSeek-V3-0324 and…

Machine Learning · Computer Science 2025-08-08 Xiaodong Chen , Mingming Ha , Zhenzhong Lan , Jing Zhang , Jianguo Li

Learning the distance metric between pairs of samples has been studied for image retrieval and clustering. With the remarkable success of pair-based metric learning losses, recent works have proposed the use of generated synthetic points on…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Byungsoo Ko , Geonmo Gu

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection…

Machine Learning · Computer Science 2023-09-18 Meng Xiao , Dongjie Wang , Min Wu , Pengfei Wang , Yuanchun Zhou , Yanjie Fu

Deep learning for recommendation data is one of the most pervasive and challenging AI workload in recent times. State-of-the-art recommendation models are one of the largest models matching the likes of GPT-3 and Switch Transformer.…

Information Retrieval · Computer Science 2022-01-25 Aditya Desai , Li Chou , Anshumali Shrivastava

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Machine Learning · Computer Science 2025-10-17 Ruijie Miao , Yilun Yao , Zihan Wang , Zhiming Wang , Bairen Yi , LingJun Liu , Yikai Zhao , Tong Yang

Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Mouxiao Huang , Borui Jiang , Dehua Zheng , Hailin Hu , Kai Han , Xinghao Chen

Deep learning recommendation systems serve personalized content under diverse tail-latency targets and input-query loads. In order to do so, state-of-the-art recommendation models rely on terabyte-scale embedding tables to learn user…

Hardware Architecture · Computer Science 2023-02-22 Samuel Hsia , Udit Gupta , Bilge Acun , Newsha Ardalani , Pan Zhong , Gu-Yeon Wei , David Brooks , Carole-Jean Wu

Collaborative filtering (CF) is a core technique for recommender systems. Traditional CF approaches exploit user-item relations (e.g., clicks, likes, and views) only and hence they suffer from the data sparsity issue. Items are usually…

Information Retrieval · Computer Science 2020-10-19 Guangneng Hu

Effective representation of data is crucial in various machine learning tasks, as it captures the underlying structure and context of the data. Embeddings have emerged as a powerful technique for data representation, but evaluating their…

Machine Learning · Computer Science 2023-09-21 Sarwan Ali

Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally…

Machine Learning · Statistics 2019-06-05 Diego Granziol , Binxin Ru , Stefan Zohren , Xiaowen Doing , Michael Osborne , Stephen Roberts

Recommender system models often represent various sparse features like users, items, and categorical features via embeddings. A standard approach is to map each unique feature value to an embedding vector. The size of the produced embedding…

Information Retrieval · Computer Science 2020-08-26 Wang-Cheng Kang , Derek Zhiyuan Cheng , Ting Chen , Xinyang Yi , Dong Lin , Lichan Hong , Ed H. Chi

Matrix factorization is one of the most efficient approaches in recommender systems. However, such algorithms, which rely on the interactions between users and items, perform poorly for "cold-users" (users with little history of such…

Information Retrieval · Computer Science 2018-05-18 ThaiBinh Nguyen , Atsuhiro Takasu

We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonly used as a pre-processing step to map these categorical…

Machine Learning · Computer Science 2025-12-02 Aodong Li , Abishek Sankararaman , Balakrishnan Narayanaswamy

In this paper, we propose a dictionary screening method for embedding compression in text classification tasks. The key purpose of this method is to evaluate the importance of each keyword in the dictionary. To this end, we first train a…

Computation and Language · Computer Science 2022-11-24 Jing Zhou , Xinru Jing , Muyu Liu , Hansheng Wang

With the development of feature extraction technique, one sample always can be represented by multiple features which locate in high-dimensional space. Multiple features can re ect various perspectives of one same sample, so there must be…

Computer Vision and Pattern Recognition · Computer Science 2018-07-30 Huibing Wang , Lin Feng , Adong Kong , Bo Jin