【综述专栏】一文了解推荐系统中的图神经网络
The following article is from RUC AI Box Author 杨晨
在科学研究中,从方法论上来讲,都应“先见森林,再见树木”。当前,人工智能学术研究方兴未艾,技术迅猛发展,可谓万木争荣,日新月异。对于AI从业者来说,在广袤的知识森林中,系统梳理脉络,才能更好地把握趋势。为此,我们精选国内外优秀的综述文章,开辟“综述专栏”,敬请关注。
© 作者|杨晨
机构|中国人民大学高瓴人工智能学院硕士
研究方向 | 推荐系统
01
[1]
[1]
02
[6]
03
推荐系统中的图神经网络分类
03
图结构建模。是在异构二部图上应用GNN,还是基于两跳近邻重构齐次图?考虑到计算效率,如何对有代表性的邻域进行图传播,而不是对整个图进行操作?
邻居聚合。如何聚合来自邻居节点的信息?具体来说,是否要区分邻居的重要性?还是要区分邻居之间的相互作用?
信息更新。如何将中心节点表示与其相邻节点的聚合表示相结合?
最终节点表示。是否使用最后一层中的节点表示,还是使用所有层中的节点表示的组合作为最终的节点表示?
社会关系的影响。社会关系中朋友有同等的影响力吗?如果没有,如何区分不同朋友的影响?
偏好集成。如何整合社会影响角度和交互行为这两方面的用户表示?
[6]
04
结语
04
参考文献
[1] https://www.bilibili.com/video/BV1Wv411h7kN?p=28
[2] Thomas N Kipf, et al. Semi-supervised classification with graph convolutional networks. ICLR 2017.
[3] William L. Hamilton, et al. Inductive Representation Learning on Large Graphs. NIPS 2017.
[4] Petar Veličković, et al. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017).
[5] Yujia Li et al. Gated graph sequence neural networks. arXiv preprint arXiv:1511.05493 (2015).
[6] Wu S, et al. Graph Neural Networks in Recommender Systems: A Survey[J]. 2020.
[7] J. Bruna, et al. Spectral networks and locally connected networks on graphs. ICLR 2014.
[8] Zonghan Wu, et al. A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems (2020).
[9] Xiang Wang, et al. Neural Graph Collaborative Filtering. SIGIR 2019.
[10] Xiangnan He, et al. LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation. SIGIR 2020.
[11] Le Wu, et al. A Neural Influence Diffusion Model for Social Recommendation. SIGIR 2019.
[12] Wenqi Fan, et al. Graph Neural Networks for Social Recommendation. WWW 2019.
[13] Hongwei Wang, et al. Knowledge Graph Convolutional Networks for Recommender Systems. WWW 2019.
[14] Xiang Wang, et al. KGAT: Knowledge Graph Attention Network for Recommendation. KDD 2019.
[15] Shu Wu, et al. Session-based recommendation with graph neural networks. AAAI 2019
[16] Chengfeng Xu, et al. Graph contextualized self-attention network for session-based recommendation. IJCAI 2019.
[17] Weiping Song, et al. Session-based social recommendation via dynamic graph attention networks. WSDM 2019.
[18] Zekun Li, et al. Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction. WWW 2019.
[19] Buru Chang, et al. Learning Graph-Based Geographical Latent Representation for Point-of-Interest Recommendation. CIKM 2020.
[20] Zhixiang He, et al. GAME: Learning Graphical and Attentive Multi-View Embeddings for Occasional Group Recommendation. SIGIR 2020.
[21] Jianxin Chang, et al. Bundle Recommendation with Graph Convolutional Networks. SIGIR 2020.
本文目的在于学术交流,并不代表本公众号赞同其观点或对其内容真实性负责,版权归原作者所有,如有侵权请告知删除。
“综述专栏”历史文章
自编码器的最佳特征:最大化互信息
系统了解Encoder-Decoder 和 Seq2Seq及其关键技术
GNN解耦表征论文汇总
最简单的self-supervised方法
Transformer结构理解及一些细节!
识别与诊断--基于深度学习的计算病理学进阶应用
BERT知识蒸馏综述
More About Attention
NLP词向量发展历程
基于深度学习的有监督关系抽取方法简介
AI系统安全的实用方法
一篇综述带你全面了解领域泛化(Domain Generalization)
到底什么是生成式对抗网络GAN?
DeepGNN: 图神经网络如何变深
Few-shot Learning 小白入门笔记
更多综述专栏文章,
请点击文章底部“阅读原文”查看
分享、点赞、在看,给个三连击呗!