Google Research

Relational inductive biases, deep learning, and graph networks

  • Peter Battaglia
  • Jessica Blake Chandler Hamrick
  • Victor Bapst
  • Alvaro Sanchez
  • Vinicius Zambaldi
  • Mateusz Malinowski
  • Andrea Tacchetti
  • David Raposo
  • Adam Santoro
  • Ryan Faulkner
  • Caglar Gulcehre
  • Francis Song
  • Andy Ballard
  • Justin Gilmer
  • George E. Dahl
  • Ashish Vaswani
  • Kelsey Allen
  • Charles Nash
  • Victoria Jayne Langston
  • Chris Dyer
  • Nicolas Heess
  • Daan Wierstra
  • Pushmeet Kohli
  • Matt Botvinick
  • Oriol Vinyals
  • Yujia Li
  • Razvan Pascanu
arXiv (2018)


The purpose of this paper is to explore relational inductive biases in modern AI, especially deep learning, describing a rough taxonomy of existing approaches, and introducing a common mathematical framework for expressing and unifying various approaches. The key theme running through this work is structure—how the world is structured, and how the structure of different computational strategies determines their strengths and weaknesses.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work