Deep learning on attributed graphs

Abstract : 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 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 working 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 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
Document type :
Theses
Complete list of metadatas

Cited literature [60 references]  Display  Hide  Download

https://pastel.archives-ouvertes.fr/tel-02085864
Contributor : Abes Star <>
Submitted on : Sunday, March 31, 2019 - 9:50:07 PM
Last modification on : Saturday, May 18, 2019 - 12:27:26 AM

File

TH2018PESC1133.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-02085864, version 1

Collections

Citation

Martin Simonovsky. Deep learning on attributed graphs. Signal and Image Processing. Université Paris-Est, 2018. English. ⟨NNT : 2018PESC1133⟩. ⟨tel-02085864⟩

Share

Metrics

Record views

101

Files downloads

44