Gated Graph Sequence Neural Networks

Published in

International Conference on Learning Representa...(2015)

External Links:

Generate Graph

TL;DR

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.

Abstract

Abstract: Graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured inputs. Our starting point is previous work on Graph Neural Networks (Scarselli et al., 2009), which we modify to use gated recurrent units and modern optimization techniques and then extend to output sequences. The result is a flexible and broadly useful class of neural network models that has favorable inductive biases relative to purely sequence-based models (e.g., LSTMs) when the problem is graph-structured. We demonstrate the capabilities on some simple AI (bAbI) and graph algorithm learning tasks. We then show it achieves state-of-the-art performance on a problem from program verification, in which subgraphs need to be matched to abstract data structures.

Authors

R. Zemel

11 papers

Yujia Li

9 papers

Marc Brockschmidt

4 papers

References39 items

Learning to Decipher the Heap for Program Verification

Document Context Language Models

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Pointer Networks

Gated Graph Sequence Neural Networks

Published in

International Conference on Learning Representa...(2015)

External Links:

Generate Graph

TL;DR

Abstract

Authors

R. Zemel

11 papers

Yujia Li

9 papers

Marc Brockschmidt

4 papers

References39 items

Learning to Decipher the Heap for Program Verification

Document Context Language Models

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Pointer Networks

Daniel Tarlow

4 papers

TL;DR

Abstract

Authors

References39 items

Learning to Decipher the Heap for Program Verification

Document Context Language Models

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Pointer Networks

TL;DR

Abstract

Authors

References39 items

Learning to Decipher the Heap for Program Verification

Document Context Language Models

Convolutional Networks on Graphs for Learning Molecular Fingerprints

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

Pointer Networks

End-To-End Memory Networks

Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

Adam: A Method for Stochastic Optimization

Neural Machine Translation by Jointly Learning to Align and Translate

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

DeepWalk: online learning of social representations

Spectral Networks and Locally Connected Networks on Graphs

Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules

Parsing Natural Scenes and Natural Language with Recursive Neural Networks

Parameter learning with truncated message-passing

Empirical Risk Minimization of Graphical Model Parameters Given Approximate Inference, Decoding, and Model Structure

Neural networks for relational learning: an experimental comparison

From machine learning to machine reasoning

Weisfeiler-Lehman Graph Kernels

Neural Network for Graphs: A Contextual Constructive Approach

A Comparison between Recursive Neural Networks and Graph Neural Networks

A new model for learning in graph domains

Marginalized Kernels Between Labeled Graphs

Separation logic: a logic for shared mutable data structures

Local Reasoning about Programs that Alter Data Structures

Global training of document processing systems using graph transformer networks

Supervised neural networks for the classification of structures

A learning rule for asynchronous perceptrons with feedback in a combinatorial environment

Generalization of back-propagation to recurrent neural networks.

Published as a conference paper at ICLR 2018 S IMULATING A CTION D YNAMICS WITH N EURAL P ROCESS N ETWORKS

Under Review as a Conference Paper at Iclr 2016 Predicting Distributions with Linearizing Belief Networks

GRASShopper - Complete Heap Verification with Mixed Specifications

Axiomatic Basis for Computer Programming

The Graph Neural Network Model

Neural methods for non-standard data

Gradient-based learning applied to document recognition

Learning task-dependent distributed representations by back-propagation through structure

Representing part-whole hierarchies in connectionist networks

Field of Study

Journal Information

Name

Venue Information

Name

Type

URL

Alternate Names