Building Graph Representations of Deep Vector Embeddings
This work introduces a novel representation method for deep learning models, potentially enabling new analytical approaches, but it is incremental as it builds on existing embedding concepts.
The paper tackles the problem of representing knowledge from pre-trained deep neural networks by proposing a graph embedding space instead of vector embeddings, and demonstrates its utility through preliminary experiments with graph analytics algorithms.
Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes. Typically, deep network representations are implemented within vector embedding spaces, which enables the use of traditional machine learning algorithms on top of them. In this short paper we propose the construction of a graph embedding space instead, introducing a methodology to transform the knowledge coded within a deep convolutional network into a topological space (i.e. a network). We outline how such graph can hold data instances, data features, relations between instances and features, and relations among features. Finally, we introduce some preliminary experiments to illustrate how the resultant graph embedding space can be exploited through graph analytics algorithms.