Skip to Main content Skip to Navigation

Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back

Martin Simonovsky 1, 2, 3 
3 imagine [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, ENPC - École des Ponts ParisTech
Abstract : A graph is a powerful concept for representation of relations between pairs of entities. Data with underlying graph structure can be found across many disciplines, describing chemical compounds, surfaces of three-dimensional models, social interactions, or knowledge bases, to name only a few. There is a natural desire for understanding such data better. Deep learning (DL) has achieved significant breakthroughs in a variety of machine learning tasks in recent years, especially where data is structured on a grid, such as in text, speech, or image understanding. However, surprisingly little has been done to explore the applicability of DL on arbitrary graph-structured data directly. The goal of this thesis is to investigate architectures for DL on graphs and study how to transfer, adapt or generalize concepts that work well on sequential and image data to this domain. We concentrate on two important primitives: embedding graphs or their nodes into a continuous vector space representation (encoding) and, conversely, generating graphs from such vectors back (decoding). To that end, we make the following contributions. First, we introduce Edge-Conditioned Convolutions (ECC), a convolution-like operation on graphs performed in the spatial domain where filters are dynamically generated based on edge attributes. The method is used to encode graphs with arbitrary and varying structure. Second, we propose SuperPoint Graph, an intermediate point cloud representation with rich edge attributes encoding the contextual relationship between object parts. Based on this representation, ECC is employed to segment large-scale point clouds without major sacrifice in fine details. Third, we present GraphVAE, a graph generator allowing us to decode graphs with variable but upper-bounded number of nodes making use of approximate graph matching for aligning the predictions of an autoencoder with its inputs. The method is applied to the task of molecule generation.
Complete list of metadata

Cited literature [209 references]  Display  Hide  Download
Contributor : Simonovsky Martin Connect in order to contact the contributor
Submitted on : Monday, February 4, 2019 - 6:59:08 PM
Last modification on : Saturday, January 15, 2022 - 3:56:40 AM
Long-term archiving on: : Sunday, May 5, 2019 - 12:40:03 PM


Files produced by the author(s)


  • HAL Id : tel-01990372, version 1



Martin Simonovsky. Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back. Machine Learning [cs.LG]. Université Paris-Est, 2018. English. ⟨tel-01990372⟩



Record views


Files downloads