Skip to Main content Skip to Navigation
New interface
Conference papers

Breaking the Limits of Message Passing Graph Neural Networks

Abstract : Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL). In this paper, we show that if the graph convolution supports are designed in spectral-domain by a nonlinear custom function of eigenvalues and masked with an arbitrary large receptive field, the MPNN is theoretically more powerful than the 1-WL test and experimentally as powerful as a 3-WL existing models, while remaining spatially localized. Moreover, by designing custom filter functions, outputs can have various frequency components that allow the convolution process to learn different relationships between a given input graph signal and its associated properties. So far, the best 3-WL equivalent graph neural networks have a computational complexity in O(n^3) with memory usage in O(n^2), consider non-local update mechanism and do not provide the spectral richness of output profile. The proposed method overcomes all these aforementioned problems and reaches state-of-the-art results in many downstream tasks.
Complete list of metadata

https://hal-normandie-univ.archives-ouvertes.fr/hal-03410699
Contributor : Paul Honeine Connect in order to contact the contributor
Submitted on : Monday, November 1, 2021 - 2:03:49 PM
Last modification on : Friday, August 5, 2022 - 11:22:16 AM
Long-term archiving on: : Wednesday, February 2, 2022 - 6:17:49 PM

File

21.icml.gnn.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03410699, version 1

Citation

Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère, Pascal Vasseur, Sébastien Adam, et al.. Breaking the Limits of Message Passing Graph Neural Networks. Proceedings of the 38th International Conference on Machine Learning (ICML), Jul 2021, Vienna, Austria. pp.599-608. ⟨hal-03410699⟩

Share

Metrics

Record views

52

Files downloads

103