Generalised Implicit Neural Representations

05/31/2022
by   Daniele Grattarola, et al.
19

We consider the problem of learning implicit neural representations (INRs) for signals on non-Euclidean domains. In the Euclidean case, INRs are trained on a discrete sampling of a signal over a regular lattice. Here, we assume that the continuous signal exists on some unknown topological space from which we sample a discrete graph. In the absence of a coordinate system to identify the sampled nodes, we propose approximating their location with a spectral embedding of the graph. This allows us to train INRs without knowing the underlying continuous domain, which is the case for most graph signals in nature, while also making the INRs equivariant under the symmetry group of the domain. We show experiments with our method on various real-world signals on non-Euclidean domains.

READ FULL TEXT

page 7

page 9

research
05/25/2023

A graphon-signal analysis of graph neural networks

We present an approach for analyzing message passing graph neural networ...
research
10/11/2021

Signal Processing on Cell Complexes

The processing of signals supported on non-Euclidean domains has attract...
research
10/27/2021

Meta-Learning Sparse Implicit Neural Representations

Implicit neural representations are a promising new avenue of representi...
research
02/04/2021

Complex Networks of Functions

Functions correspond to one of the key concepts in mathematics and scien...
research
05/01/2019

A Unified Deep Learning Formalism For Processing Graph Signals

Convolutional Neural Networks are very efficient at processing signals d...
research
08/21/2023

Approximately Equivariant Graph Networks

Graph neural networks (GNNs) are commonly described as being permutation...
research
01/07/2019

Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation

Convolutional Neural Networks (CNN) have been successful in processing d...

Please sign up or login with your details

Forgot password? Click here to reset