Binary Graph Neural Networks - IRT Saint Exupéry - Institut de Recherche Technologique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Binary Graph Neural Networks

Résumé

Graph Neural Networks (GNNs) have emerged as a powerful and flexible framework for representation learning on irregular data. As they generalize the operations of classical CNNs on grids to arbitrary topologies, GNNs also bring much of the implementation challenges of their Euclidean counterparts. Model size, memory footprint, and energy consumption are common concerns for many realworld applications. Network binarization allocates a single bit to parameters and activations, thus dramatically reducing the memory requirements (up to 32x compared to single-precision floating-point numbers) and maximizing the benefits of fast SIMD instructions on modern hardware for measurable speedups. However, in spite of the large body of work on binarization for classical CNNs, this area remains largely unexplored in geometric deep learning. In this paper, we present and evaluate different strategies for the binarization of graph neural networks. We show that through careful design of the models, and control of the training process, binary graph neural networks can be trained at only a moderate cost in accuracy on challenging benchmarks. In particular, we present the first dynamic graph neural network in Hamming space, able to leverage efficient k-NN search on binary vectors to speed-up the construction of the dynamic graph. We further verify that the binary models offer significant savings on embedded devices. Our code is publicly available on Github.
Fichier principal
Vignette du fichier
main.pdf (435.46 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03184720 , version 1 (29-03-2021)

Identifiants

  • HAL Id : hal-03184720 , version 1

Citer

Mehdi Bahri, Gaétan Bahl, Stefanos Zafeiriou. Binary Graph Neural Networks. CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, IEEE, Jun 2021, Nashville / Virtual, United States. ⟨hal-03184720⟩
176 Consultations
205 Téléchargements

Partager

Gmail Facebook X LinkedIn More