PathBoost extends path-based gradient boosting with logistic loss, prefix-based multi-attribute handling, and automatic anchor selection, achieving better or comparable results to GNNs and graph kernels on benchmark datasets, especially larger graphs.
and Grohe, Martin and Fey, Matthias and Borgwardt, Karsten , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Path-Based Gradient Boosting for Graph-Level Prediction
PathBoost extends path-based gradient boosting with logistic loss, prefix-based multi-attribute handling, and automatic anchor selection, achieving better or comparable results to GNNs and graph kernels on benchmark datasets, especially larger graphs.