Bi-Lipschitz encoders in neural graph matching provide controlled GED surrogates and better alignment costs, leading to improved prediction and ranking on benchmarks.
How powerful are graph neural networks? InInternational Conference on Learning Representations
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Characterizes monotone separating set functions with dimension bounds, proves non-existence on infinite domains, and introduces a Holder-stable neural model with a weak version of the property for universal monotone approximation.
citing papers explorer
-
Towards Metric-Faithful Neural Graph Matching
Bi-Lipschitz encoders in neural graph matching provide controlled GED surrogates and better alignment costs, leading to improved prediction and ranking on benchmarks.
-
Monotone and Separable Set Functions: Characterizations and Neural Models
Characterizes monotone separating set functions with dimension bounds, proves non-existence on infinite domains, and introduces a Holder-stable neural model with a weak version of the property for universal monotone approximation.