DeepAI AI Chat
Log In Sign Up

SIGN: Scalable Inception Graph Neural Networks

by   Emanuele Rossi, et al.

Geometric deep learning, a novel class of machine learning algorithms extending classical deep learning architectures to non-Euclidean structured data such as manifolds and graphs, has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media. In this paper, we propose SIGN, a scalable graph neural network analogous to the popular inception module used in classical convolutional architectures. We show that our architecture is able to effectively deal with large-scale graphs via pre-computed multi-scale neighborhood features. Extensive experimental evaluation on various open benchmarks shows the competitive performance of our approach compared to a variety of popular architectures, while requiring a fraction of training and inference time.


page 1

page 2

page 3

page 4


Geometric deep learning on graphs and manifolds using mixture model CNNs

Deep learning has achieved a remarkable performance breakthrough in seve...

Differentiable Graph Module (DGM) Graph Convolutional Networks

Graph deep learning has recently emerged as a powerful ML concept allowi...

Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods

Many widely used datasets for graph machine learning tasks have generall...

Learning through structure: towards deep neuromorphic knowledge graph embeddings

Computing latent representations for graph-structured data is an ubiquit...

Geometric deep learning: going beyond Euclidean data

Many scientific fields study data with an underlying structure that is a...

GPNet: Simplifying Graph Neural Networks via Multi-channel Geometric Polynomials

Graph Neural Networks (GNNs) are a promising deep learning approach for ...

Scalable Geometric Deep Learning on Molecular Graphs

Deep learning in molecular and materials sciences is limited by the lack...

Code Repositories


SIGN: Scalable Inception Graph Network

view repo


In this project I carried out at EURECOM university I deeply delve into the theory of Graph Convolutional Networks and explore solutions for anomaly detection on huge financial graphs.

view repo