paper-with-me

홈 › Papers

Single-shot Embedding Dimension Search in Recommender System

2022-04-07 · Liang Qu, Yonghong Ye, Ningzhi Tang, Lixin Zhang, Yuhui Shi, Hongzhi Yin

As a crucial component of most modern deep recommender systems, feature embedding maps high-dimensional sparse user/item features into low-dimensional dense embeddings. However, these embeddings are usually assigned a unified dimension, which suffers from the following issues: (1) high memory usage and computation cost. (2) sub-optimal performance due to inferior dimension assignments. In order to alleviate the above issues, some works focus on automated embedding dimension search by formulating it as hyper-parameter optimization or embedding pruning problems. However, they either require well-designed search space for hyperparameters or need time-consuming optimization procedures. In this paper, we propose a Single-Shot Embedding Dimension Search method, called SSEDS, which can efficiently assign dimensions for each feature field via a single-shot embedding pruning operation while maintaining the recommendation accuracy of the model. Specifically, it introduces a criterion for identifying the importance of each embedding dimension for each feature field. As a result, SSEDS could automatically obtain mixed-dimensional embeddings by explicitly reducing redundant embedding dimensions based on the corresponding dimension importance ranking and the predefined parameter budget. Furthermore, the proposed SSEDS is model-agnostic, meaning that it could be integrated into different base recommendation models. The extensive offline experiments are conducted on two widely used public datasets for CTR prediction tasks, and the results demonstrate that SSEDS can still achieve strong recommendation performance even if it has reduced 90\% parameters. Moreover, SSEDS has also been deployed on the WeChat Subscription platform for practical recommendation services. The 7-day online A/B test results show that SSEDS can significantly improve the performance of the online recommendation model.

📄 PDF Abstract BibTeX arXiv:2204.03281

Code (0)

등록된 구현이 없습니다.

Tasks

Click-Through Rate PredictionRecommendation Systems

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

iHAS: Instance-wise Hierarchical Architecture Search for Deep Learning Recommendation Models

2023-09-14 · Yakun Yu, Shi-ang Qi, Jiuding Yang, Liyao Jiang 외

Current recommender systems employ large-sized embedding tables with uniform dimensions for all features, leading to overfitting, high computational cost, and suboptimal generalizing performance. Many techniques aim to s…

Clusteringfeature selectionNeural Architecture SearchRecommendation Systems

AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations

2020-02-26 · Xiangyu Zhao, Chong Wang, Ming Chen, Xudong Zheng 외

Deep learning based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimensionality of categorical variables (e.g. user/item identifiers) and meaningfully transform them in the lo…

AutoMLRecommendation Systems

Differentiable Neural Input Search for Recommender Systems

2020-06-08 · Weiyu Cheng, Yanyan Shen, Linpeng Huang

Latent factor models are the driving forces of the state-of-the-art recommender systems, with an important insight of vectorizing raw input features into dense embeddings. The dimensions of different feature embeddings a…

Click-Through Rate PredictionRecommendation Systems

i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems

2022-04-01 · Yao Yao, Bin Liu, Haoxun He, Dakui Sheng 외

Input features play a crucial role in DNN-based recommender systems with thousands of categorical and continuous fields from users, items, contexts, and interactions. Noisy features and inappropriate embedding dimension …

Click-Through Rate PredictionFeature Engineeringfeature selectionNeural Architecture Search+1

Embedding in Recommender Systems: A Survey

2023-10-28 · Xiangyu Zhao, Maolin Wang, Xinjian Zhao, Jiansheng Li 외

Recommender systems have become an essential component of many online platforms, providing personalized recommendations to users. A crucial aspect is embedding techniques that coverts the high-dimensional discrete featur…

AutoMLCollaborative FilteringQuantizationRecommendation Systems+2