Deep Tabular Learning

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.

Source: Boost then Convolve: Gradient Boosting Meets Graph Neural Networks


Paper Code Results Date Stars


Task Papers Share
Graph Representation Learning 1 100.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign