Embeddings and Representation Learning for Structured Data
This is an incremental survey paper that summarizes existing techniques for representation learning on structured data, relevant for researchers and practitioners in machine learning fields dealing with non-vectorial data.
The paper provides a high-level overview of state-of-the-art methods for constructing vectorial representations of structured data, addressing the challenge that such data lacks a natural vector form, and surveys approaches like kernel methods, neural networks, and recent developments such as graph convolutional networks.
Performing machine learning on structured data is complicated by the fact that such data does not have vectorial form. Therefore, multiple approaches have emerged to construct vectorial representations of structured data, from kernel and distance approaches to recurrent, recursive, and convolutional neural networks. Recent years have seen heightened attention in this demanding field of research and several new approaches have emerged, such as metric learning on structured data, graph convolutional neural networks, and recurrent decoder networks for structured data. In this contribution, we provide an high-level overview of the state-of-the-art in representation learning and embeddings for structured data across a wide range of machine learning fields.