Tuned feature-only MLPs nearly match graph neural networks on five common graph benchmarks, suggesting those benchmarks measure feature quality more than graph learning.
Bronstein, Joan Bruna, Y
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting the Necessity of Graph Learning and Common Graph Benchmarks
Tuned feature-only MLPs nearly match graph neural networks on five common graph benchmarks, suggesting those benchmarks measure feature quality more than graph learning.