GCNIII, a wide linear plus deep graph convolution hybrid, achieves slightly higher node classification accuracy than GCNII on several benchmarks by adding a linear branch and tuning hyperparameters per dataset.
Simple and deep graph convolutional networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Wide & Deep Learning for Node Classification
GCNIII, a wide linear plus deep graph convolution hybrid, achieves slightly higher node classification accuracy than GCNII on several benchmarks by adding a linear branch and tuning hyperparameters per dataset.