GraphiT: Encoding Graph Structure in Transformers - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

GraphiT: Encoding Graph Structure in Transformers

Abstract

We show that viewing graphs as sets of node features and incorporating structural and positional information into a transformer architecture is able to outperform representations learned with classical graph neural networks (GNNs). Our model, GraphiT, encodes such information by (i) leveraging relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs, and (ii) enumerating and encoding local sub-structures such as paths of short length. We thoroughly evaluate these two ideas on many classification and regression tasks, demonstrating the effectiveness of each of them independently, as well as their combination. In addition to performing well on standard benchmarks, our model also admits natural visualization mechanisms for interpreting graph motifs explaining the predictions, making it a potentially strong candidate for scientific applications where interpretation is important.
Fichier principal
Vignette du fichier
GraphiT.pdf (734.89 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03256708 , version 1 (10-06-2021)

Identifiers

  • HAL Id : hal-03256708 , version 1

Cite

Grégoire Mialon, Dexiong Chen, Margot Selosse, Julien Mairal. GraphiT: Encoding Graph Structure in Transformers. 2021. ⟨hal-03256708⟩
1827 View
997 Download

Share

Gmail Mastodon Facebook X LinkedIn More