TREE-G: Decision Trees Contesting Graph Neural Networks

Maya Bechler-Speicher, Amir Globerson, Ran Gilad-Bachrach

Research output: Contribution to journalConference articlepeer-review


When dealing with tabular data, models based on decision trees are a popular choice due to their high accuracy on these data types, their ease of application, and explainability properties. However, when it comes to graph-structured data, it is not clear how to apply them effectively, in a way that incorporates the topological information with the tabular data available on the vertices of the graph. To address this challenge, we introduce TREE-G. TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data. Not only does this split function incorporate the node features and the topological information, but it also uses a novel pointer mechanism that allows split nodes to use information computed in previous splits. Therefore, the split function adapts to the predictive task and the graph at hand. We analyze the theoretical properties of TREE-G and demonstrate its benefits empirically on multiple graph and vertex prediction benchmarks. In these experiments, TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks and Graph Kernels, sometimes by large margins. Moreover, TREE-Gs models and their predictions can be explained and visualized.

Original languageEnglish
Pages (from-to)11032-11042
Number of pages11
JournalProceedings of the AAAI Conference on Artificial Intelligence
Issue number10
StatePublished - 25 Mar 2024
Event38th AAAI Conference on Artificial Intelligence, AAAI 2024 - Vancouver, Canada
Duration: 20 Feb 202427 Feb 2024


FundersFunder number
Tel Aviv University
Israel Science Foundation1186/18, 1437/22


    Dive into the research topics of 'TREE-G: Decision Trees Contesting Graph Neural Networks'. Together they form a unique fingerprint.

    Cite this