论文标题
使用图形自动编码器和应用程序的应用程序对代表性学习的贡献
Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
论文作者
论文摘要
Graph AutoCododers（GAE）和变分图自动编码器（VGAE）成为两个强大的无监督节点嵌入方法的组，以及针对基于图的机器学习问题的各种应用，例如链接预测和社区检测。尽管如此，在该博士学位开始时Project，GAE和VGAE模型也受到关键局限性，阻止了行业中的采用。在本文中，我们为改善这些模型提供了一些贡献，其总体目的是促进它们用于解决涉及图表表示的工业级别问题。首先，我们提出了两种策略来克服先前GAE和VGAE模型的可伸缩性问题，从而允许在具有数百万个节点和边缘的大图上有效训练这些模型。这些策略分别利用图形退化和随机子图解码技术。此外，我们引入了重力启发的GAE和VGAE，为有向图的这些模型提供了第一个扩展，这些模型在工业应用中无处不在。我们还考虑用于动态图的GAE和VGAE模型的扩展。此外，我们认为GAE和VGAE模型通常不必要地复杂，我们建议通过利用线性编码来简化它们。最后，我们介绍了模块化感知的GAE和VGAE，以改善图形上的社区检测，同时在链接预测上共同保留良好的表现。在本文的最后一部分中，我们在从音乐流媒体服务节目中提取的几个图表上评估了我们的方法。我们强调基于图的音乐推荐问题。特别是，我们表明我们的方法可以改善对用户推荐的类似音乐项目的社区的检测，以便他们可以在寒冷的开始环境中有效地对类似的艺术家进行排名，并且它们允许对整个文化的音乐流派感知进行建模。
Graph autoencoders (GAE) and variational graph autoencoders (VGAE) emerged as two powerful groups of unsupervised node embedding methods, with various applications to graph-based machine learning problems such as link prediction and community detection. Nonetheless, at the beginning of this Ph.D. project, GAE and VGAE models were also suffering from key limitations, preventing them from being adopted in the industry. In this thesis, we present several contributions to improve these models, with the general aim of facilitating their use to address industrial-level problems involving graph representations. Firstly, we propose two strategies to overcome the scalability issues of previous GAE and VGAE models, permitting to effectively train these models on large graphs with millions of nodes and edges. These strategies leverage graph degeneracy and stochastic subgraph decoding techniques, respectively. Besides, we introduce Gravity-Inspired GAE and VGAE, providing the first extensions of these models for directed graphs, that are ubiquitous in industrial applications. We also consider extensions of GAE and VGAE models for dynamic graphs. Furthermore, we argue that GAE and VGAE models are often unnecessarily complex, and we propose to simplify them by leveraging linear encoders. Lastly, we introduce Modularity-Aware GAE and VGAE to improve community detection on graphs, while jointly preserving good performances on link prediction. In the last part of this thesis, we evaluate our methods on several graphs extracted from the music streaming service Deezer. We put the emphasis on graph-based music recommendation problems. In particular, we show that our methods can improve the detection of communities of similar musical items to recommend to users, that they can effectively rank similar artists in a cold start setting, and that they permit modeling the music genre perception across cultures.
