Paper Info
Title
Relational inductive biases, deep learning, and graph networks.
Abstract
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond oneu0027s experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between hand-engineering and end-to-end learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning. As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.
Year
Venue
Field
2018
arXiv: Learning
Human intelligence,Generalization,Nature versus nurture,Unification,Position paper,Software,Artificial intelligence,Deep learning,Artificial neural network,Machine learning,Mathematics
DocType
Volume
Citations 
Journal
abs/1806.01261
74
PageRank 
References 
Authors
1.41
100
27
Name
Order
Citations
PageRank
Peter Battaglia144222.63
Jessica B. Hamrick2742.43
Victor Bapst31435.38
Alvaro Sanchez-Gonzalez41036.21
Vinícius Flores Zambaldi522810.31
Mateusz Malinowski655224.68
Andrea Tacchetti71389.57
David Raposo8945.89
Adam Santoro943820.37
Ryan Faulkner101084.48
Çaglar Gülçehre113010133.22
H. Francis Song121055.14
Andrew J. Ballard131063.48
justin gilmer1437516.71
George E. Dahl154734416.42
Ashish Vaswani1690132.81
Kelsey Allen171027.30
Charles Nash1812216.27
Victoria Langston19972.90
chris dyer205438232.28
Nicolas Heess21176294.77
Daan Wierstra225412255.92
Pushmeet Kohli237398332.84
Matthew Botvinick24741.41
Oriol Vinyals259419418.45
Yujia Li2640523.01
Razvan Pascanu272596199.21