Graph neural networks

G Corso, H Stark, S Jegelka, T Jaakkola… - Nature Reviews …, 2024 - nature.com
Graphs are flexible mathematical objects that can represent many entities and knowledge
from different domains, including in the life sciences. Graph neural networks (GNNs) are …

Expressive sign equivariant networks for spectral geometric learning

D Lim, J Robinson, S Jegelka… - Advances in Neural …, 2024 - proceedings.neurips.cc
Recent work has shown the utility of develo** machine learning models that respect the
structure and symmetries of eigenvectors. These works promote sign invariance, since for …

Swingnn: Rethinking permutation invariance in diffusion models for graph generation

Q Yan, Z Liang, Y Song, R Liao, L Wang - arxiv preprint arxiv:2307.01646, 2023 - arxiv.org
Diffusion models based on permutation-equivariant networks can learn permutation-
invariant distributions for graph data. However, in comparison to their non-invariant …

An efficient subgraph gnn with provable substructure counting power

Z Yan, J Zhou, L Gao, Z Tang, M Zhang - Proceedings of the 30th ACM …, 2024 - dl.acm.org
We investigate the enhancement of graph neural networks'(GNNs) representation power
through their ability in substructure counting. Recent advances have seen the adoption of …

Probability graphons: the right convergence point of view

G Zucal - arxiv preprint arxiv:2407.05998, 2024 - arxiv.org
We extend the theory of probability graphons, continuum representations of edge-decorated
graphs arising in graph limits theory, to the'right convergence'point of view. First of all, we …

Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs

M Cordonnier, N Keriven, N Tremblay… - arxiv preprint arxiv …, 2023 - arxiv.org
We study the convergence of message passing graph neural networks on random graph
models to their continuous counterpart as the number of nodes tends to infinity. Until now …

Convergence of Message-Passing Graph Neural Networks with Generic Aggregation on Large Random Graphs

M Cordonnier, N Keriven, N Tremblay… - Journal of Machine …, 2024 - jmlr.org
We study the convergence of message-passing graph neural networks on random graph
models toward their continuous counterparts as the number of nodes tends to infinity. Until …

Unsupervised Graph Representation Learning beyond Aggregated View

J Zhou, J Li, L Kuang, N Gui - IEEE Transactions on Knowledge …, 2024 - ieeexplore.ieee.org
Unsupervised graph representation learning aims to condense graph information into dense
vector embeddings to support various downstream tasks. To achieve this goal, existing …

Universal Local Attractors on Graphs

E Krasanakis, S Papadopoulos, I Kompatsiaris - Applied Sciences, 2024 - mdpi.com
Being able to express broad families of equivariant or invariant attributed graph functions is
a popular measuring stick of whether graph neural networks should be employed in …

From Learning to Optimize to Learning Optimization Algorithms

C Castera, P Ochs - arxiv preprint arxiv:2405.18222, 2024 - arxiv.org
Towards designing learned optimization algorithms that are usable beyond their training
setting, we identify key principles that classical algorithms obey, but have up to now, not …