• Corpus ID: 11309193

A Generalization of Convolutional Neural Networks to Graph-Structured Data

@article{Hechtlinger2017AGO,
  title={A Generalization of Convolutional Neural Networks to Graph-Structured Data},
  author={Yotam Hechtlinger and Purvasha Chakravarti and Jining Qin},
  journal={ArXiv},
  year={2017},
  volume={abs/1704.08165}
}
This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. [] Key Method Furthermore, this generalization can be applied to many standard regression or classification problems, by learning the the underlying graph. We empirically demonstrate the performance of the proposed CNN on MNIST, and challenge the state-of-the-art on Merck molecular activity data set.

Figures and Tables from this paper

Local-Aggregation Graph Networks
TLDR
By replacing the traditional convolution in CNNs with the parameterized local-aggregation function, Local-Aggregation Graph Networks (LAGNs) are readily established, which enable to fit nonlinear functions without activation functions and can be expediently trained with the standard back-propagation.
Learning Representations of Graph Data - A Survey
TLDR
The objective of this survey is to summarize and discuss the latest advances in methods to Learn Representations of Graph Data, and identify the major approaches used for learning representations of graph data.
Dynamic Filters in Graph Convolutional Neural Networks
TLDR
A novel method to adapt the behaviour of a GCNN to the input is presented proposing two ways to perform spatial convolution on graphs using input-based filters which are dynamically generated.
CAYLEYNETS: SPECTRAL GRAPH CNNS WITH COMPLEX RATIONAL FILTERS
TLDR
A new spectral domain convolutional architecture for deep learning on graphs with a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest.
Adaptive Filters in Graph Convolutional Neural Networks
TLDR
A novel method to adapt the behaviour of a ConvGNN to the input is presented proposing a method to perform spatial convolution on graphs using input-specific filters, which are dynamically generated from nodes feature vectors.
Hypergraph-Induced Convolutional Networks for Visual Classification
TLDR
The proposed hypergraph-induced convolutional network framework is a framework to explore the high-order correlation in visual data during deep neural networks that combines a hypergraph structure and a learning process based on the constructed hypergraph.
CayleyNets: Graph Convolutional Neural Networks With Complex Rational Spectral Filters
TLDR
A new spectral domain convolutional architecture for deep learning on graphs with a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest.
Development of Generic CNN Deep Learning Method Using Feature Graph
TLDR
This work developed a method to tackle the issue and make CNN applicable by endowing meaning to the sequence of non-structured data, and demonstrated its effectiveness by adding improvements.
Kernel-Weighted Graph Convolutional Network: A Deep Learning Approach for Traffic Forecasting
TLDR
A novel Kernel-Weighted Graph Convolutional Network (KW-GCN) for traffic forecasting, which learns simultaneously a group of convolutional kernels and their linear combination weights for each of the nodes in the graph, which yields a mechanism that is able to learn the features locally and exploit the structure information of traffic road-network globally.
...
...

References

SHOWING 1-10 OF 26 REFERENCES
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
TLDR
This work presents a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.
Deep Convolutional Networks on Graph-Structured Data
TLDR
This paper develops an extension of Spectral Networks which incorporates a Graph Estimation procedure, that is test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.
Diffusion-Convolutional Neural Networks
TLDR
Through the introduction of a diffusion-convolution operation, it is shown how diffusion-based representations can be learned from graph-structured data and used as an effective basis for node classification.
Semi-Supervised Classification with Graph Convolutional Networks
TLDR
A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
Spectral Networks and Locally Connected Networks on Graphs
TLDR
This paper considers possible generalizations of CNNs to signals defined on more general domains without the action of a translation group, and proposes two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian.
Geometric Deep Learning: Going beyond Euclidean data
TLDR
Deep neural networks are used for solving a broad range of problems from computer vision, natural-language processing, and audio analysis where the invariances of these structures are built into networks used to model them.
The Graph Neural Network Model
TLDR
A new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains, and implements a function tau(G,n) isin IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space.
Gated Graph Sequence Neural Networks
TLDR
This work studies feature learning techniques for graph-structured inputs and achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.
A new model for learning in graph domains
TLDR
A new neural model, called graph neural network (GNN), capable of directly processing graphs, which extends recursive neural networks and can be applied on most of the practically useful kinds of graphs, including directed, undirected, labelled and cyclic graphs.
Convolutional Networks on Graphs for Learning Molecular Fingerprints
TLDR
A convolutional neural network that operates directly on graphs that allows end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape is introduced.
...
...