Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization.
Tien Huu DoDuc Minh NguyenGiannis BekoulisAdrian MunteanuNikos DeligiannisPublished in: CoRR (2020)
Keyphrases
- message passing
- transition probabilities
- convolutional neural networks
- random walk
- singly connected
- directed graph
- graph structure
- markov chain
- markov random walk
- belief propagation
- distributed systems
- markov models
- undirected graph
- shared memory
- graphical models
- markov random field
- max product
- sum product
- web graph
- spanning tree
- junction tree
- markov model
- link structure
- weighted graph
- stereo matching
- depth map
- maximum likelihood
- higher order
- sum product algorithm
- machine learning