推荐系统系列文章(序幕篇)-facebook出品的DLRM

Posted 2021-05-01 算法工程师学习笔记

推荐系统文章笔记，第一篇文章分享的是Facebook的Deep Learning Recommendation Model for Personalization and Recommendation Systems[https://arxiv.org/abs/1906.00091]。这篇这篇文章没有提出什么十分新颖的网络结构，但是涵盖了目前工业界深度ctr预估问题的主流的网络模块，可以体现现在工业界的推荐系统建设的一个趋势方向。

最后这篇文章也介绍了依赖于Pytorch的分布式的训练方法，是一篇实用性非常强的文章，并且在Kaggle的真实数据集合上取得了SOTA的效果。

参考文献

[1] Naumov, M., Mudigere, D., Shi, H.M., Huang, J., Sundaraman, N., Park, J., Wang, X., Gupta, U., Wu, C., Azzolini, A.G., Dzhulgakov, D., Mallevich, A., Cherniavskii, I., Lu, Y., Krishnamoorthi, R., Yu, A., Kondratenko, V.Y., Pereira, S., Chen, X., Chen, W., Rao, V., Jia, B., Xiong, L., & Smelyanskiy, M. (2019). Deep Learning Recommendation Model for Personalization and Recommendation Systems. ArXiv, abs/1906.00091.

[2] Rendle, S. (2010). Factorization Machines. international conference on data mining.

[3] Guo, H., Tang, R., Ye, Y., Li, Z., & He, X. (2017). DeepFM: A Factorization-Machine based Neural Network for CTR Prediction. IJCAI.

[4] Wang, R., Fu, B., Fu, G., & Wang, M. (2017). Deep & Cross Network for Ad Click Predictions. ADKDD'17.

[5] Lian, J., Zhou, X., Zhang, F., Chen, Z., Xie, X., & Sun, G. (2018). xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.