[论文解读] Signed Graph Convolutional Network

Tyler Derr, Yao Ma+1 more|arXiv (Cornell University)|Aug 20, 2018

Advanced Graph Neural Networks参考文献 27被引用 56

一句话总结

提出了带符号的图卷积网络（SGCN），利用均衡理论在带符号网络中整合正负链接，从而实现有效的节点嵌入和边符号预测。它通过在多层中沿着平衡路径和非平衡路径聚合信息，并以基于均衡理论的损失进行优化。

ABSTRACT

Due to the fact much of today's data can be represented as graphs, there has been a demand for generalizing neural network models for graph data. One recent direction that has shown fruitful results, and therefore growing interest, is the usage of graph convolutional neural networks (GCNs). They have been shown to provide a significant improvement on a wide range of tasks in network analysis, one of which being node representation learning. The task of learning low-dimensional node representations has shown to increase performance on a plethora of other tasks from link prediction and node classification, to community detection and visualization. Simultaneously, signed networks (or graphs having both positive and negative links) have become ubiquitous with the growing popularity of social media. However, since previous GCN models have primarily focused on unsigned networks (or graphs consisting of only positive links), it is unclear how they could be applied to signed networks due to the challenges presented by negative links. The primary challenges are based on negative links having not only a different semantic meaning as compared to positive links, but their principles are inherently different and they form complex relations with positive links. Therefore we propose a dedicated and principled effort that utilizes balance theory to correctly aggregate and propagate the information across layers of a signed GCN model. We perform empirical experiments comparing our proposed signed GCN against state-of-the-art baselines for learning node representations in signed networks. More specifically, our experiments are performed on four real-world datasets for the classical link sign prediction problem that is commonly used as the benchmark for signed network embeddings algorithms.

研究动机与目标

• 激励在链接可能为正或负的带符号网络中学习节点表示。
• 提出一个遵循均衡理论、用于聚合正信息和负信息的原理性 GCN 变体。
• 开发一个指导带符号关系嵌入学习的目标函数。
• 证明在真实世界的带符号网络上用于边符号预测的有效性。）

提出的方法

• 通过引入基于平衡路径和非平衡路径的聚合，将无符号 GCN 扩展到带符号网络。
• 定义 B(l) 和 U(l) 集合，以利用均衡理论捕捉层 l（及以下） 的平衡路径和非平衡路径。
• 在每一层为每个节点维护两种表示：一个“朋友”（平衡）表示和一个“敌人”（非平衡）表示。
• 使用带权矩阵 W^(l) 的层级聚合器，分别从 N_i^+(正) 和 N_i^-(负) 传播信息。
• 提出算法 2，通过连接 h_i^{B(L)} 和 h_i^{U(L)} 来为每个节点生成最终嵌入。
• 形成一个目标函数，包含用于边类型分类的有监督多项式逻辑回归部分，以及基于扩展结构平衡理论的第二项，通过带正则化的 SGD 进行优化。

实验结果

研究问题

• RQ1 SGCN 是否能够为带符号网络中的节点学习出有意义的低维嵌入？
• RQ2 将均衡理论和更长的聚合路径纳入是否能相较于基线提升带符号网络的嵌入？
• RQ3 平衡路径和非平衡路径聚合如何影响边符号的预测性能？
• RQ4 仅使用第一层聚合与多层基于均衡理论的聚合相比，其影响是什么？

主要发现

• SGCN 在四个真实世界的带符号网络上用于边符号预测的性能优于最新的基线方法。
• 结合均衡理论和更长路径的信息，提升了嵌入质量，相较于单层聚合。
• 该模型为每个节点学习了两种表示（朋友和敌人），通过平衡/非平衡路径在多层中有效传播。
• 目标函数将一个有监督分类器项与一个基于均衡理论的排序项结合，以构建嵌入空间。