On over-squashing in message passing neural networks: The impact of width, depth, and topology
Abstract Message Passing Neural Networks (MPNNs) are instances of Graph Neural
Networks that leverage the graph to send messages over the edges. This inductive bias …
Networks that leverage the graph to send messages over the edges. This inductive bias …
Revisiting over-smoothing and over-squashing using ollivier-ricci curvature
Abstract Graph Neural Networks (GNNs) had been demonstrated to be inherently
susceptible to the problems of over-smoothing and over-squashing. These issues prohibit …
susceptible to the problems of over-smoothing and over-squashing. These issues prohibit …
Locality-aware graph-rewiring in gnns
Graph Neural Networks (GNNs) are popular models for machine learning on graphs that
typically follow the message-passing paradigm, whereby the feature of a node is updated …
typically follow the message-passing paradigm, whereby the feature of a node is updated …
On the trade-off between over-smoothing and over-squashing in deep graph neural networks
Graph Neural Networks (GNNs) have succeeded in various computer science applications,
yet deep GNNs underperform their shallow counterparts despite deep learning's success in …
yet deep GNNs underperform their shallow counterparts despite deep learning's success in …
Two heads are better than one: Boosting graph sparse training via semantic and topological awareness
Graph Neural Networks (GNNs) excel in various graph learning tasks but face computational
challenges when applied to large-scale graphs. A promising solution is to remove non …
challenges when applied to large-scale graphs. A promising solution is to remove non …
Over-squashing in graph neural networks: A comprehensive survey
S Akansha - arXiv preprint arXiv:2308.15568, 2023 - arxiv.org
Graph Neural Networks (GNNs) have emerged as a revolutionary paradigm in the realm of
machine learning, offering a transformative approach to dissect intricate relationships …
machine learning, offering a transformative approach to dissect intricate relationships …
How does over-squashing affect the power of GNNs?
Graph Neural Networks (GNNs) are the state-of-the-art model for machine learning on graph-
structured data. The most popular class of GNNs operate by exchanging information …
structured data. The most popular class of GNNs operate by exchanging information …
Probabilistically rewired message-passing neural networks
Message-passing graph neural networks (MPNNs) emerged as powerful tools for
processing graph-structured input. However, they operate on a fixed input graph structure …
processing graph-structured input. However, they operate on a fixed input graph structure …
Cooperative graph neural networks
Graph neural networks are popular architectures for graph machine learning, based on
iterative computation of node representations of an input graph through a series of invariant …
iterative computation of node representations of an input graph through a series of invariant …
Mitigating over-smoothing and over-squashing using augmentations of Forman-Ricci curvature
Abstract While Graph Neural Networks (GNNs) have been successfully leveraged for
learning on graph-structured data across domains, several potential pitfalls have been …
learning on graph-structured data across domains, several potential pitfalls have been …