We propose an extension of the Contextual Graph Markov Model, a deep and
probabilistic machine learning model for graphs, to model the distribution of
edge features. Our approach is architectural, as we introduce an additional
Bayesian network mapping edge features into discrete states to be used by the
original model. In doing so, we are also able to build richer graph
representations even in the absence of edge features, which is confirmed by the
performance improvements on standard graph classification benchmarks. Moreover,
we successfully test our proposal in a graph regression scenario where edge
features are of fundamental importance, and we show that the learned edge
representation provides substantial performance improvements against the
original model on three link prediction tasks. By keeping the computational
complexity linear in the number of edges, the proposed model is amenable to
large-scale graph processing.

我们扩展了上下文图马尔可夫模型，采用深度且概率的机器学习模型来建模边特征的分布。我们在架构上进行了改进，将边特征映射成离散状态的贝叶斯网络，并用于原始模型。通过这样做，即使在没有边特征的情况下，我们也能构建更丰富的图表示，通过在标准图分类基准测试中的性能改进得到了证实。此外，在边特征至关重要的图回归场景中成功测试了我们的提议，我们展示了所学到的边表示在三个链接预测任务上相对于原始模型的重大性能改进。由于计算复杂度与边数量线性相关，该提议的模型适用于大规模图处理。

建模深度贝叶斯图网络中的边特征

Modeling Edge Features with Deep Bayesian Graph Networks

We introduce the Contextual Graph Markov Model, an approach combining ideas
from generative models and neural networks for the processing of graph data. It
founds on a constructive methodology to build a deep architecture comprising
layers of probabilistic models that learn to encode the structured information
in an incremental fashion. Context is diffused in an efficient and scalable way
across the graph vertexes and edges. The resulting graph encoding is used in
combination with discriminative models to address structure classification
benchmarks.

本文介绍了一种结合了生成模型和神经网络思想的上下文图马尔科夫模型，其基于一种构造性方法来构建深度架构，通过逐步学习编码结构化信息。这种图编码方法与判别模型结合可用于解决结构分类问题。