A benchmark of 7 GNNs and 30 losses on 3 graphs claims hybrid losses and GIN rank best on average, but a central summary table contradicts the paper's full results.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Evaluating Loss Functions for Graph Neural Networks: Towards Pretraining and Generalization
A benchmark of 7 GNNs and 30 losses on 3 graphs claims hybrid losses and GIN rank best on average, but a central summary table contradicts the paper's full results.