Graph neural networks
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 …
from different domains, including in the life sciences. Graph neural networks (GNNs) are …
Expressive sign equivariant networks for spectral geometric learning
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 …
structure and symmetries of eigenvectors. These works promote sign invariance, since for …
Swingnn: Rethinking permutation invariance in diffusion models for graph generation
Diffusion models based on permutation-equivariant networks can learn permutation-
invariant distributions for graph data. However, in comparison to their non-invariant …
invariant distributions for graph data. However, in comparison to their non-invariant …
An efficient subgraph gnn with provable substructure counting power
We investigate the enhancement of graph neural networks'(GNNs) representation power
through their ability in substructure counting. Recent advances have seen the adoption of …
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 …
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
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 …
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
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 …
models toward their continuous counterparts as the number of nodes tends to infinity. Until …
Unsupervised Graph Representation Learning beyond Aggregated View
Unsupervised graph representation learning aims to condense graph information into dense
vector embeddings to support various downstream tasks. To achieve this goal, existing …
vector embeddings to support various downstream tasks. To achieve this goal, existing …
Universal Local Attractors on Graphs
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 …
a popular measuring stick of whether graph neural networks should be employed in …
From Learning to Optimize to Learning Optimization Algorithms
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 …
setting, we identify key principles that classical algorithms obey, but have up to now, not …