【论文笔记】Learning Convolutional Neural Networks for Graphs

【论文笔记】Learning Convolutional Neural Networks for Graphs

Learning Convolutional Neural Networks for Graphs

2018-01-17  21:41:57

【Introduction】

这篇 paper 是发表在 ICML 2016 的:http://jmlr.org/proceedings/papers/v48/niepert16.pdf

【论文笔记】Learning Convolutional Neural Networks for Graphs

上图展示了传统 CNN 在 image 上进行卷积操作的工作流程。(a)就是通过滑动窗口的形式,利用3*3 的卷积核在 image 上进行滑动,来感知以某一个像素点为中心的局部图像区域(local image patch);(b)感受野所创建的 node sequence,以及由超参数所决定的感受野的形状。

本文将 CNN 拓展到大规模的基于 graph 的学习问题当中,主要考虑如下两类问题:

1. 给定一组 graphs,学习一个函数,使之可以在 unseen graphs 用于 classification 或者 regression problem。

The nodes of any two graphs are not necessarily in correspondence. For instance, each graph of the collection could model a chemical compound and the output could be a function mapping unseen compounds to their level of activity against cancer cells.

2. 给定一个大型的 graph,学习 graph 的表示,使其可以用于推理不可见的 graph 属性,例如:node types 或者 missing edges。

本文提出一种学习表示的框架来进行 有向图 和 无向图的分类。这个图可能拥有多个离散和连续属性的 nodes 和 edges,可能包含多种类型的 edges。与传统CNN 相比,我们从 input graphs 中获得 locally connected neighborhoods。这些近邻 可以有效的产生,并且作为卷积结构的感受野,允许该框架学习有效的 graph representation。

For numerous graph collections a problem-specific ordering (spatial, temporal, or otherwise) is missing and the nodes of the graphs are not in correspondence. In these instances, one has to solve two problems:

  (i) Determining the node sequences for which neighborhood graphs are created;

  (ii) computing a normalization of neighborhood graphs, that is, a unique mapping from a graph representation into a vector space representation. 

而本文所提出的 graph representation 的方法,很好的解决了上述两个问题。具体的来说,可以分为如下几个步骤:

  1. 对于每一个输入的 graph,首先确定节点及其次序;(For each input graph, it first determines nodes (and their order) for which neighborhood graphs are created.

  2. 对于每一个节点,包含 k 个节点的近邻 被提取并且进行归一化,即,将其唯一的映射到固定长度的线性序列;归一化的近邻 可以看做是一个节点的感受野;(For each of these nodes, a neighborhood consisting of exactly k nodes is extracted and normalized, that is, it is uniquely mapped to a space with a fixed linear order. The normalized neighborhood serves as the receptive field for a node under consideration.)

  3. 最后,特征学习成分,例如 卷积、全连接层 被组合起来作用于归一化的 graphs。(Finally, feature learning components such as convolutional and dense layers are combined with the normalized neighborhood graphs as the CNN’s receptive fields.

【论文笔记】Learning Convolutional Neural Networks for Graphs


【流程】下面具体介绍一下构建卷积分片的步骤以及最后的卷积结构:

  1. 节点序列选择:为了对图中所有的节点进行标号排序,本文引入了图标号函数,将图中的节点集合根据向心性(节点的度、中心度等)映射为有序的节点序列。从该序列中根据一定的间隔s隔段选取w个节点构成最终的节点序列。

  2. 邻居节点收集:对于上一步获得的节点序列中的每一个节点,利用广度优化搜索扩展邻居节点,和源节点一起构成一个k大小的邻域集合。

  3. 子图规范化:对于一个邻域集合的规划化过程如下图所示。对邻域集合中的个节点按照标号函数k进行排序,得到接受域。那么,对于节点的属性,k个节点属性值构成了一个输入通道,对于边的属性,k^2个属性值也构成了一个输入通道。我们可以分别用一维的卷积层来处理这两种输入通道(对于节点属性卷积层长度为k,对于边属性卷积层长度为k^2)

【论文笔记】Learning Convolutional Neural Networks for Graphs

 【论文笔记】Learning Convolutional Neural Networks for Graphs

【论文笔记】Learning Convolutional Neural Networks for Graphs


Reference:

1. 知乎博客:https://zhuanlan.zhihu.com/p/27587371   

2. 对应的 PDF:http://www.matlog.net/icml2016_slides.pdf