Learning Embeddings of Directed Networks with Text-Associated Nodes---with Applications in Software Package Dependency Networks

TL;DR

This paper introduces two neural network algorithms, PCTADW-1 and PCTADW-2, for learning embeddings of directed networks with text, demonstrated on software package dependency networks, showing improved classification and analogy properties.

Contribution

The paper presents novel algorithms for embedding directed networks with text, specifically applied to software dependency networks, and uncovers analogy phenomena in such embeddings.

Findings

Embeddings outperform baselines in node classification.

Analogies similar to word embeddings are observed in network embeddings.

Network embeddings help understand software attributes.

Abstract

A network embedding consists of a vector representation for each node in the network. Its usefulness has been shown in many real-world application domains, such as social networks and web networks. Directed networks with text associated with each node, such as software package dependency networks, are commonplace. However, to the best of our knowledge, their embeddings have hitherto not been specifically studied. In this paper, we propose PCTADW-1 and PCTADW-2, two algorithms based on neural networks that learn embeddings of directed networks with text associated with each node. We create two new node-labeled such networks: The package dependency networks in two popular GNU/Linux distributions, Debian and Fedora. We experimentally demonstrate that the embeddings produced by our algorithms resulted in node classification with better quality than those of various baselines on these two networks. We observe that there exist systematic presence of analogies (similar to those in word embeddings) in the network embeddings of software package dependency networks. To the best of our knowledge, this is the first time that such systematic presence of analogies is observed in network and document embeddings. We further demonstrate that these network embeddings can be novelly used for better understanding software attributes, such as the development process and user interface of software, etc.