GSEBO learns edge strengths in graph neural networks via bi-level optimization, using validation loss as the outer objective, and reports improved node classification on four graphs.
Forward and reverse gradient-based hyperparameter optimization
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
-
Graph Structure Learning with Bi-level Optimization
GSEBO learns edge strengths in graph neural networks via bi-level optimization, using validation loss as the outer objective, and reports improved node classification on four graphs.