Boost then Convolve: Gradient Boosting Meets Graph Neural Networks

Sergei Ivanov, Liudmila Prokhorenkova

Keywords: GNN, GBDT, graphs, tabular data, heterogeneous data

Abstract: Graph neural networks (GNNs) are powerful models that have been successful in various graph representation learning tasks. Whereas gradient boosted decision trees (GBDT) often outperform other machine learning methods when faced with heterogeneous tabular data. But what approach should be used for graphs with tabular node features? Previous GNN models have mostly focused on networks with homogeneous sparse features and, as we show, are suboptimal in the heterogeneous setting. In this work, we propose a novel 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. Our model benefits from end-to-end optimization by allowing new trees to fit the gradient updates of GNN. With an extensive experimental comparison to the leading GBDT and GNN models, we demonstrate a significant increase in performance on a variety of graphs with tabular features. The code is available: https://github.com/nd7141/bgnn.

One-sentence Summary: A novel strong architecture that combines advantages of GBDT and GNN for node-level prediction problems on graphs with tabular data.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Code: [ nd7141/bgnn](https://github.com/nd7141/bgnn)

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2101.08543/code)