Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

SpatialSim: Recognizing Spatial Configurations of Objects with Graph Neural Networks

Laetitia Teodorescu 1 Katja Hofmann 2 Pierre-Yves Oudeyer 1
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : Recognizing precise geometrical configurations of groups of objects is a key capability of human spatial cognition, yet little studied in the deep learning literature so far. In particular, a fundamental problem is how a machine can learn and compare classes of geometric spatial configurations that are invariant to the point of view of an external observer. In this paper we make two key contributions. First, we propose SpatialSim (Spatial Similarity), a novel geometrical reasoning benchmark, and argue that progress on this benchmark would pave the way towards a general solution to address this challenge in the real world. This benchmark is composed of two tasks: Identification and Comparison, each one instantiated in increasing levels of difficulty. Secondly, we study how relational inductive biases exhibited by fully-connected message-passing Graph Neural Networks (MPGNNs) are useful to solve those tasks, and show their advantages over less relational baselines such as Deep Sets and unstructured models such as Multi-Layer Perceptrons. Finally, we highlight the current limits of GNNs in these tasks.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas
Contributor : Laetitia Teodorescu <>
Submitted on : Thursday, January 21, 2021 - 4:12:53 PM
Last modification on : Friday, January 29, 2021 - 9:45:27 AM


Files produced by the author(s)


  • HAL Id : hal-03117819, version 1
  • ARXIV : 2004.04546



Laetitia Teodorescu, Katja Hofmann, Pierre-Yves Oudeyer. SpatialSim: Recognizing Spatial Configurations of Objects with Graph Neural Networks. 2021. ⟨hal-03117819⟩



Record views


Files downloads