AICurious Logo

What is: Boost-GNN?

SourceBoost then Convolve: Gradient Boosting Meets Graph Neural Networks
Data SourceCC BY-SA -

Boost-GNN is an architecture that trains GBDT and GNN jointly to get the best of both worlds: the GBDT model deals with heterogeneous features, while GNN accounts for the graph structure. The model benefits from end-to-end optimization by allowing new trees to fit the gradient updates of GNN.