AutoDPQ: Automated Differentiable Product Quantization for Embedding Compression
Pages 1833 - 1837
Abstract
Deep recommender systems typically involve numerous feature fields for users and items, with a large number of low-frequency features. These low-frequency features would reduce the prediction accuracy with large storage space due to their vast quantity and inadequate training. Some pioneering studies have explored embedding compression techniques to address this issue of the trade-off between storage space and model predictability. However, these methods have difficulty compacting the embedding of low-frequency features in various feature fields due to the high demand for human experience and computing resources during hyper-parameter searching. In this paper, we propose the AutoDPQ framework, which automatically compacts low-frequency feature embeddings for each feature field to an adaptive magnitude. Experimental results indicate that AutoDPQ can significantly reduce the parameter space while improving recommendation accuracy. Moreover, AutoDPQ is compatible with various deep CTR models by improving their performance significantly with high efficiency.
References
[1]
Bo Chen, Xiangyu Zhao, Yejing Wang, Wenqi Fan, Huifeng Guo, and Ruiming Tang. 2022. Automated Machine Learning for Deep Recommender Systems: A Survey. arXiv preprint arXiv:2204.01390 (2022).
[2]
Ting Chen, Lala Li, and Yizhou Sun. 2020. Differentiable product quantization for end-to-end embedding compression. In ICML. 1617--1626.
[3]
Ting Chen, Martin Renqiang Min, and Yizhou Sun. 2018. Learning k-way d-dimensional discrete codes for compact embedding representations. In ICML. 854--863.
[4]
Huifeng Guo, Ruiming Tang, Yunming Ye, Zhenguo Li, and Xiuqiang He. 2017. DeepFM: a factorization-machine based neural network for CTR prediction. In IJCAI.
[5]
Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016).
[6]
Wei Jin, Xiaorui Liu, Xiangyu Zhao, Yao Ma, Neil Shah, and Jiliang Tang. 2022. Automated Self-Supervised Learning for Graphs. In 10th International Conference on Learning Representations (ICLR 2022).
[7]
Wang-Cheng Kang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi, Ting Chen, Lichan Hong, and Ed H Chi. 2021. Learning to embed categorical features without embedding tables for recommendation. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 840--850.
[8]
Muyang Li, Zijian Zhang, Xiangyu Zhao, Wanyu Wang, Minghao Zhao, Runze Wu, and Ruocheng Guo. 2023. AutoMLP: Automated MLP for Sequential Recommendations. In Proceedings of the Web Conference 2023.
[9]
Weilin Lin, Xiangyu Zhao, Yejing Wang, Tong Xu, and Xian Wu. 2022. AdaFS: Adaptive Feature Selection in Deep Recommender System. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 3309--3317.
[10]
Weilin Lin, Xiangyu Zhao, Yejing Wang, Yuanshao Zhu, and Wanyu Wang. 2023. AutoDenoise: Automatic Data Instance Denoising for Recommendations. In Proceedings of the Web Conference 2023.
[11]
Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. Darts: Differentiable architecture search. arXiv preprint arXiv:1806.09055 (2018).
[12]
Haochen Liu, Xiangyu Zhao, Chong Wang, Xiaobing Liu, and Jiliang Tang. 2020. Automated Embedding Size Search in Deep Recommender Systems. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2307--2316.
[13]
Yanru Qu, Han Cai, Kan Ren, Weinan Zhang, Yong Yu, Ying Wen, and Jun Wang. 2016. Product-based neural networks for user response prediction. In ICDM. IEEE, 1149--1154.
[14]
Fengyi Song, Bo Chen, Xiangyu Zhao, Huifeng Guo, and Ruiming Tang. 2022. AutoAssign: Automatic Shared Embedding Assignment in Streaming Recommendation. In 2022 IEEE International Conference on Data Mining (ICDM). IEEE, 458--467.
[15]
Ruoxi Wang, Bin Fu, Gang Fu, and Mingliang Wang. 2017. Deep & cross network for ad click predictions. In ADKDD. 1--7.
[16]
Yejing Wang, Xiangyu Zhao, Tong Xu, and Xian Wu. 2022. Autofield: Automating feature selection in deep recommender systems. In Proceedings of the ACM Web Conference 2022. 1977--1986.
[17]
Caojin Zhang, Yicun Liu, Yuanpu Xie, Sofia Ira Ktena, Alykhan Tejani, Akshay Gupta, Pranay Kumar Myana, Deepak Dilipkumar, Suvadip Paul, Ikuhiro Ihara, et al. 2020. Model size reduction using frequency based double hashing for recommender systems. In RecSys. 521--526.
[18]
Xiangyu Zhao. 2022. Adaptive and automated deep recommender systems. ACM SIGWEB Newsletter Spring (2022), 1--4.
[19]
Xiangyu Zhao, Changsheng Gu, Haoshenglun Zhang, Xiwang Yang, Xiaobing Liu, Hui Liu, and Jiliang Tang. 2021a. DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 750--758.
[20]
Xiangyu Zhao, Haochen Liu, Wenqi Fan, Hui Liu, Jiliang Tang, and Chong Wang. 2021b. AutoLoss: Automated Loss Function Search in Recommendations. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 3959--3967.
[21]
Xiangyu Zhao, Haochen Liu, Wenqi Fan, Hui Liu, Jiliang Tang, Chong Wang, Ming Chen, Xudong Zheng, Xiaobing Liu, and Xiwang Yang. 2021c. Autoemb: Automated embedding dimensionality search in streaming recommendations. In 2021 IEEE International Conference on Data Mining (ICDM). IEEE, 896--905.
[22]
Xiangyu Zhao, Haochen Liu, Hui Liu, Jiliang Tang, Weiwei Guo, Jun Shi, Sida Wang, Huiji Gao, and Bo Long. 2021d. AutoDim: Field-aware Embedding Dimension Searchin Recommender Systems. In Proceedings of the Web Conference 2021. 3015--3022.
[23]
Chenxu Zhu, Bo Chen, Huifeng Guo, Hang Xu, Xiangyang Li, Xiangyu Zhao, Weinan Zhang, Yong Yu, Ruiming Tang, Wenwu Ou, et al. 2023. AutoGen: An Automated Dynamic Model Generation Framework for Recommender System. In Proceedings of the 16th ACM International Conference on Web Search and Data Mining. 445--453.
Index Terms
- AutoDPQ: Automated Differentiable Product Quantization for Embedding Compression
Recommendations
Self-embedding watermarking scheme against JPEG compression with superior imperceptibility
To improve the imperceptibility, security and tamper detection performance, a self-embedding watermarking scheme against JPEG compression is proposed in this work. The recovery watermark of all blocks in the host image, which consists of 6-bit DC-code ...
An Information-Hiding Scheme Based on Quantization-Based Embedding Technique
Information hiding is a technique that embeds secret data in digital media for using in a variety of applications, including ownership protection, authentication, access control, annotation and so on. In this paper, we propose an information hiding ...
A Sequential Quantization Strategy for Data Embedding and Integrity Verification
Quantization-based embedding has been used for integrity verification in semi-fragile watermarking. However, some of the illegal modifications cannot be detected in the normal quantization-based methods, especially when the host values (i.e., the values ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
July 2023
3567 pages
ISBN:9781450394086
DOI:10.1145/3539618
- General Chairs:
- Hsin-Hsi Chen,
- Wei-Jou (Edward) Duh,
- Hen-Hsen Huang,
- Program Chairs:
- Makoto P. Kato,
- Josiane Mothe,
- Barbara Poblete
Copyright © 2023 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 18 July 2023
Check for updates
Qualifiers
- Short-paper
Funding Sources
- SIRG - CityU Strategic Interdisciplinary Research Grant
- APRC - CityU New Research Initiatives
- Ant Group (CCF-Ant Research Fund)
- CityU - HKIDS Early Career Research Grant
- Huawei (Huawei Innovation Research Program)
- Ant Group Research Fund
Conference
SIGIR '23
Sponsor:
SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval
July 23 - 27, 2023
Taipei, Taiwan
Acceptance Rates
Overall Acceptance Rate 792 of 3,983 submissions, 20%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 286Total Downloads
- Downloads (Last 12 months)126
- Downloads (Last 6 weeks)13
Reflects downloads up to 13 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in