Using Hierarchically Connected Nodes and Multiple GNN Message Passing Steps to Increase the Contextual Information in Cell-Graph Classification.
Joe SimsHeike Irmgard GrabschDerek MageePublished in: ISGIE/GRAIL@MICCAI (2022)
Keyphrases
- contextual information
- message passing
- belief propagation
- graph classification
- context aware
- sum product
- distributed systems
- high level
- markov random field
- multiple types
- graphical models
- higher order
- dynamic programming
- vector space
- pairwise
- machine learning
- prior knowledge
- network structure
- object recognition
- kernel matrix