Search Results for author:
Found 11 papers, 7 papers with code
Can strong structural encoding reduce the importance of Message Passing?
This suggests that the importance of message passing is limited when the model can construct strong structural encodings.
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 recursively upon aggregating information over its neighbors.
How does over-squashing affect the power of GNNs?
In this paper, we provide a rigorous analysis to determine which function classes of node features can be learned by an MPNN of a given capacity.
Edge Directionality Improves Learning on Heterophilic Graphs
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data.
Ranked #1 on
Node Classification
on snap-patents
DRew: Dynamically Rewired Message Passing with Delay
Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions.
Ranked #1 on
Graph Classification
on Peptides-func
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
Our analysis provides a unified framework to study different recent methods introduced to cope with over-squashing and serves as a justification for a class of methods that fall under graph rewiring.
Understanding convolution on graphs via energies
We do so by showing that linear graph convolutions with symmetric weights minimize a multi-particle energy that generalizes the Dirichlet energy; in this setting, the weight matrices induce edge-wise attraction (repulsion) through their positive (negative) eigenvalues, thereby controlling whether the features are being smoothed or sharpened.
Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs
In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour.
Heterogeneous manifolds for curvature-aware graph embedding
Graph embeddings, wherein the nodes of the graph are represented by points in a continuous space, are used in a broad range of Graph ML applications.
Understanding over-squashing and bottlenecks on graphs via curvature
Most graph neural networks (GNNs) use the message passing paradigm, in which node features are propagated on the input graph.
Ranked #43 on
Node Classification
on Citeseer
Beltrami Flow and Neural Diffusion on Graphs
We propose a novel class of graph neural networks based on the discretised Beltrami flow, a non-Euclidean diffusion PDE.
