Skip to main content
Artificial Intelligence

Return to Question

Bumped by Community user
Bumped by Community user
Bumped by Community user
Bumped by Community user
added 33 characters in body; edited tags; edited title
Source Link
nbro
nbro
  • 41.4k
  • 12
  • 115
  • 205

How can we derive a CNN (ConvolutionConvolution Neural Net.)Network from a more generic GNN (GraphGraph Neural Net.)Network?

CNNsConvolution Neural Network (Conv. neural netsCNNs) operate over strict grid-like structures (MxNxC$M \times N \times C$ images), whereas GNNsGraph Neural Networks (Graph neural nets.GNNs) can operate over all-flexible graphs, with an undefined number of neighbors and edges. On

On the face of it, GNNs appear to be neural architectures that can subsume CNNs. Are GNNs really generalized architectures that can operate arbitrary functions over arbitrary graph structures? An

An obvious followupfollow-  up - How can we derive a CNN out of a GNN?

Since non-spectral GNNs are based on message-passing that employ permutation-invariant functions, is it possible to derive a CNN from a base-architecture of GNN  ?

How can we derive a CNN (Convolution Neural Net.) from a more generic GNN (Graph Neural Net.)?

CNNs (Conv. neural nets) operate over strict grid-like structures (MxNxC images) whereas GNNs (Graph neural nets.) can operate over all-flexible graphs, with undefined number of neighbors and edges. On the face of it, GNNs appear to be neural architectures that can subsume CNNs. Are GNNs really generalized architectures that can operate arbitrary functions over arbitrary graph structures? An obvious followup-  How can we derive a CNN out of a GNN?

Since non-spectral GNNs are based on message-passing that employ permutation-invariant functions, is it possible to derive a CNN from a base-architecture of GNN  ?

How can we derive a Convolution Neural Network from a more generic Graph Neural Network?

Convolution Neural Network (CNNs) operate over strict grid-like structures ($M \times N \times C$ images), whereas Graph Neural Networks (GNNs) can operate over all-flexible graphs, with an undefined number of neighbors and edges.

On the face of it, GNNs appear to be neural architectures that can subsume CNNs. Are GNNs really generalized architectures that can operate arbitrary functions over arbitrary graph structures?

An obvious follow-up - How can we derive a CNN out of a GNN?

Since non-spectral GNNs are based on message-passing that employ permutation-invariant functions, is it possible to derive a CNN from a base-architecture of GNN?

Source Link
Kris
Kris
  • 39
  • 1

How can we derive a CNN (Convolution Neural Net.) from a more generic GNN (Graph Neural Net.)?

CNNs (Conv. neural nets) operate over strict grid-like structures (MxNxC images) whereas GNNs (Graph neural nets.) can operate over all-flexible graphs, with undefined number of neighbors and edges. On the face of it, GNNs appear to be neural architectures that can subsume CNNs. Are GNNs really generalized architectures that can operate arbitrary functions over arbitrary graph structures? An obvious followup- How can we derive a CNN out of a GNN?

Since non-spectral GNNs are based on message-passing that employ permutation-invariant functions, is it possible to derive a CNN from a base-architecture of GNN ?