RecSys 2019最佳论文:基于深度学习的推荐系统是否真的优于传统经典方法?
作者丨纪厚业
单位丨北京邮电大学博士生
研究方向丨异质图神经网络,异质图表示学习和推荐系统
本文发表在推荐系统顶会 RecSys 2019 并获得了 Best Paper。作者梳理实现了大量顶会推荐论文的代码方便大家入门推荐系统。
传送门:
https://github.com/MaurizioFD/RecSys2019_DeepLearning_Evaluation
引言
相关论文、模型评价标准及基线算法
模型验证
Collaborative Deep Learning (CDL)
可以看出,随着 list 长度的增加,CDL 效果逐渐超过一些 baseline,但是和最佳 baseline(ItemKNN-CBF)的差距依然较大。
https://www.zhihu.com/question/336304380/answer/784976195
SpectralCF 表现不是很好,
结论
本文复现并分析了近些年各大顶会的 18 篇推荐论文。结果表明,仅仅有 7 篇论文可以复现,但是其效果并不一定比一些基础推荐算法好。这不禁让作者怀疑深度推荐系统这个领域是否真正的取得了进步。
参考文献
[1] Travis Ebesu, Bin Shen, and Yi Fang. 2018. Collaborative Memory Network for Recommendation Systems. In Proceedings SIGIR ’18. 515–524.
[2] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural collaborative fltering. In Proceedings WWW ’17. 173–182.
[3] Binbin Hu, Chuan Shi, Wayne Xin Zhao, and Philip S Yu. 2018. Leveraging meta-path based context for top-n recommendation with a neural co-attention model. In Proceedings KDD ’18. 1531–1540.
[4] Xiaopeng Li and James She. 2017. Collaborative variational autoencoder for recommender systems. In Proceedings KDD ’17. 305–314.
[5] Dawen Liang, Rahul G Krishnan, Matthew D Hofman, and Tony Jebara. 2018. Variational Autoencoders for Collaborative Filtering. In Proceedings WWW ’18. 689–698.
[6] Hao Wang, Naiyan Wang, and Dit-Yan Yeung. 2015. Collaborative deep learning for recommender systems. In Proceedings KDD ’15. 1235–1244.
[7] Lei Zheng, Chun-Ta Lu, Fei Jiang, Jiawei Zhang, and Philip S. Yu. 2018. Spectral Collaborative Filtering. In Proceedings RecSys ’18. 311–319.
[8] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. 2018. Multi-Pointer Co-Attention Networks for Recommendation. In Proceedings SIGKDD ’18. 2309–2318.
[9] Zhu Sun, Jie Yang, Jie Zhang, Alessandro Bozzon, Long-Kai Huang, and Chi Xu. 2018. Recurrent Knowledge Graph Embedding for Efective Recommendation. In Proceedings RecSys ’18. 297–305.
[10] Homanga Bharadhwaj, Homin Park, and Brian Y. Lim. 2018. RecGAN: Recurrent Generative Adversarial Networks for Recommendation Systems. In Proceedings RecSys ’18. 372–376.
[11] Noveen Sachdeva, Kartik Gupta, and Vikram Pudi. 2018. Attentive Neural Architecture Incorporating Song Features for Music Recommendation. In Proceedings RecSys ’18. 417–421.
[12] Trinh Xuan Tuan and Tu Minh Phuong. 2017. 3D Convolutional Networks for Session-based Recommendation with Content Features. In Proceedings RecSys ’17. 138–146.
[13] Donghyun Kim, Chanyoung Park, Jinoh Oh, Sungyoung Lee, and Hwanjo Yu. 2016. Convolutional Matrix Factorization for Document Context-Aware Recommendation. In Proceedings RecSys ’16. 233–240.
[14] Flavian Vasile, Elena Smirnova, and Alexis Conneau. 2016. Meta-Prod2Vec: Product Embeddings Using Side-Information for Recommendation. In Proceedings RecSys ’16. 225–232.
[15] Jarana Manotumruksa, Craig Macdonald, and Iadh Ounis. 2018. A Contextual Attention Recurrent Architecture for Context-Aware Venue Recommendation. In Proceedings SIGIR ’18. 555–564.
[16] Jingyuan Chen, Hanwang Zhang, Xiangnan He, Liqiang Nie, Wei Liu, and Tat-Seng Chua. 2017. Attentive collaborative fltering: Multimedia recommendation with item-and component-level attention. In Proceedings SIGIR ’17. 335–344.
[17] Yi Tay, Luu Anh Tuan, and Siu Cheung Hui. 2018. Latent relational metric learning via memory-based attention for collaborative ranking. In Proceedings WWW ’18. 729–739.
[18] Ali Mamdouh Elkahky, Yang Song, and Xiaodong He. 2015. A multi-view deep learning approach for cross domain user modeling in recommendation systems. In Proceedings WWW ’15. 278–288.
点击以下标题查看更多往期内容:
让你的论文被更多人看到
如何才能让更多的优质内容以更短路径到达读者群体,缩短读者寻找优质内容的成本呢?答案就是:你不认识的人。
总有一些你不认识的人,知道你想知道的东西。PaperWeekly 或许可以成为一座桥梁,促使不同背景、不同方向的学者和学术灵感相互碰撞,迸发出更多的可能性。
PaperWeekly 鼓励高校实验室或个人,在我们的平台上分享各类优质内容,可以是最新论文解读,也可以是学习心得或技术干货。我们的目的只有一个,让知识真正流动起来。
📝 来稿标准:
• 稿件确系个人原创作品,来稿需注明作者个人信息(姓名+学校/工作单位+学历/职位+研究方向)
• 如果文章并非首发,请在投稿时提醒并附上所有已发布链接
• PaperWeekly 默认每篇文章都是首发,均会添加“原创”标志
📬 投稿邮箱:
• 投稿邮箱:hr@paperweekly.site
• 所有文章配图,请单独在附件中发送
• 请留下即时联系方式(微信或手机),以便我们在编辑发布时和作者沟通
🔍
现在,在「知乎」也能找到我们了
进入知乎首页搜索「PaperWeekly」
点击「关注」订阅我们的专栏吧
关于PaperWeekly
PaperWeekly 是一个推荐、解读、讨论、报道人工智能前沿论文成果的学术平台。如果你研究或从事 AI 领域,欢迎在公众号后台点击「交流群」,小助手将把你带入 PaperWeekly 的交流群里。
▽ 点击 | 阅读原文 | 下载论文 & 源码