Bi-Lipschitz encoders in neural graph matching provide controlled GED surrogates and better alignment costs, leading to improved prediction and ranking on benchmarks.
H2mn: Graph similarity learning with hierarchical hypergraph matching networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.