13.5. 小结¶
推荐系统作为深度学习在工业界最成功的落地成果之一，极大地提升了用户的在线使用体验，并且为各大公司创造了可观的利润，从而促使各大公司持续加大对推荐系统的投入。过去两年推荐模型的规模成指数增长，带来了许多系统层面的挑战亟待解决。在实际的生产环境中面临的问题与挑战是本章区区几千字难以概括的，因此工业级推荐系统的架构必然十分复杂，本章只能抛砖引玉地简单介绍一种典型的推荐系统组成的基本架构和运行过程，并介绍了推荐系统面临的持续更新模型的挑战和一种前沿的解决方案。面对实际生产环境，具体的系统设计方案需要根据不同推荐场景的需求而变化，不存在一种万能的解决方案。
13.6. 扩展阅读¶
推荐模型：Wide & Deep
消息队列介绍：什么是消息队列
特征存储介绍：什么是机器学习中的特征存储
13.7. 参考文献¶
- Cheng et al., 2016
Cheng, H.-T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., … others. (2016). Wide & deep learning for recommender systems. Proceedings of the 1st workshop on deep learning for recommender systems (pp. 7–10).
- Chilimbi et al., 2014
Chilimbi, T., Suzue, Y., Apacible, J., & Kalyanaraman, K. (2014 , October). Project adam: building an efficient and scalable deep learning training system. 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14) (pp. 571–582). Broomfield, CO: USENIX Association. URL: https://www.usenix.org/conference/osdi14/technical-sessions/presentation/chilimbi
- SouzaPereiraMoreira et al., 2021
de Souza Pereira Moreira, G., Rabhi, S., Lee, J. M., Ak, R., & Oldridge, E. (2021). Transformers4rec: bridging the gap between nlp and sequential/session-based recommendation. Proceedings of the 15th ACM Conference on Recommender Systems (pp. 143–153).
- Li et al., 2014
Li, M., Andersen, D. G., Park, J. W., Smola, A. J., Ahmed, A., Josifovski, V., … Su, B.-Y. (2014 , October). Scaling distributed machine learning with the parameter server. 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14) (pp. 583–598). Broomfield, CO: USENIX Association. URL: https://www.usenix.org/conference/osdi14/technical-sessions/presentation/li_mu
- Ma et al., 2018
Ma, X., Zhao, L., Huang, G., Wang, Z., Hu, Z., Zhu, X., & Gai, K. (2018). Entire space multi-task model: an effective approach for estimating post-click conversion rate. The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval (pp. 1137–1140).
- Malkhi et al., 2007
Malkhi, D., Novik, L., & Purcell, C. (2007 , April). P2p replica synchronization with vector sets. SIGOPS Oper. Syst. Rev., 41(2), 68–74. URL: https://doi.org/10.1145/1243418.1243427, doi:10.1145/1243418.1243427
- Malkhi & Terry, 2005
Malkhi, D., & Terry, D. (2005). Fraigniaud, P. (Ed.). Concise version vectors in winfs. Distributed Computing (pp. 339–353). Berlin, Heidelberg: Springer Berlin Heidelberg.
- Merity et al., 2016
Merity, S., Xiong, C., Bradbury, J., & Socher, R. (2016). Pointer sentinel mixture models. arXiv preprint arXiv:1609.07843.
- Naumov et al., 2019
Naumov, M., Mudigere, D., Shi, H.-J. M., Huang, J., Sundaraman, N., Park, J., … others. (2019). Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:1906.00091.
- Russakovsky et al., 2015
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., … Bernstein, M. (2015). Imagenet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV), 115(3), 211–252.
- Sima et al., 2022
Sima, C., Fu, Y., Sit, M.-K., Guo, L., Gong, X., Lin, F., … Mai, L. (2022 , July). Ekko: a Large-Scale deep learning recommender system with Low-Latency model update. 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22) (pp. 821–839). Carlsbad, CA: USENIX Association. URL: https://www.usenix.org/conference/osdi22/presentation/sima
- Yi et al., 2019
Yi, X., Yang, J., Hong, L., Cheng, D. Z., Heldt, L., Kumthekar, A., … Chi, E. (2019). Sampling-bias-corrected neural modeling for large corpus item recommendations. Proceedings of the 13th ACM Conference on Recommender Systems (pp. 269–277).