Rethinking graph transformers with spectral attention

D Kreuzer, D Beaini, W Hamilton… - Advances in …, 2021 - proceedings.neurips.cc
In recent years, the Transformer architecture has proven to be very successful in sequence
processing, but its application to other data structures, such as graphs, has remained limited …

Understanding oversquashing in gnns through the lens of effective resistance

M Black, Z Wan, A Nayyeri… - … Conference on Machine …, 2023 - proceedings.mlr.press
Message passing graph neural networks (GNNs) are a popular learning architectures for
graph-structured data. However, one problem GNNs experience is oversquashing, where a …

Riemannian flow matching on general geometries

RTQ Chen, Y Lipman - ar**: clinical tools, algorithms and approaches for understanding the arrhythmogenic substrate
S Coveney, C Cantwell, C Roney - Medical & Biological Engineering & …, 2022 - Springer
Characterizing patient-specific atrial conduction properties is important for understanding
arrhythmia drivers, for predicting potential arrhythmia pathways, and for personalising …

Registration of 3D point clouds and meshes: A survey from rigid to nonrigid

GKL Tam, ZQ Cheng, YK Lai… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
Three-dimensional surface registration transforms multiple three-dimensional data sets into
the same coordinate system so as to align overlap** components of these sets. Recent …

A survey on shape correspondence

O Van Kaick, H Zhang, G Hamarneh… - Computer graphics …, 2011 - Wiley Online Library
We review methods designed to compute correspondences between geometric shapes
represented by triangle meshes, contours or point sets. This survey is motivated in part by …

Geodesics in heat: A new approach to computing distance based on heat flow

K Crane, C Weischedel, M Wardetzky - ACM Transactions on Graphics …, 2013 - dl.acm.org
We introduce the heat method for computing the geodesic distance to a specified subset (eg,
point or curve) of a given domain. The heat method is robust, efficient, and simple to …

Spatially aggregating spectral descriptors for nonrigid 3D shape retrieval: a comparative survey

C Li, A Ben Hamza - Multimedia Systems, 2014 - Springer
This paper presents a comprehensive review and analysis of recent spectral shape
descriptors for nonrigid 3D shape retrieval. More specifically, we compare the latest spectral …

Hunt for the unique, stable, sparse and fast feature learning on graphs

S Verma, ZL Zhang - Advances in Neural Information …, 2017 - proceedings.neurips.cc
For the purpose of learning on graphs, we hunt for a graph feature representation that
exhibit certain uniqueness, stability and sparsity properties while also being amenable to …

The heat method for distance computation

K Crane, C Weischedel, M Wardetzky - Communications of the ACM, 2017 - dl.acm.org
We introduce the heat method for solving the single-or multiple-source shortest path
problem on both flat and curved domains. A key insight is that distance computation can be …