Building powerful and equivariant graph neural networks with message-passing.
Clément VignacAndreas LoukasPascal FrossardPublished in: CoRR (2020)
Keyphrases
- message passing
- neural network
- belief propagation
- distributed systems
- probabilistic inference
- factor graphs
- markov random field
- shared memory
- junction tree
- tree reweighted
- inference in graphical models
- max product
- graph cuts
- approximate inference
- singly connected
- graphical models
- sum product algorithm
- distributed shared memory
- stereo matching
- back propagation
- higher order
- preprocessing
- ldpc codes
- clustering algorithm