Research map / Graph learning / Graph algorithms and clustering

Bridging Graph Worlds: Neural Approximation of Gromov-Wasserstein Distances

NeurIPS 2026 · Graph learning › Graph algorithms and clustering · approach: Graph distance and retrieval

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes neural approximation of Gromov-Wasserstein distances between graphs to avoid the expensive non-convex GW optimization.

Problem

Computing the Gromov-Wasserstein distance between graphs requires solving a complex non-convex optimization problem, which is computationally expensive.

Approach

Uses neural networks to approximate GW distances between graphs, as a faster surrogate for the exact non-convex optimization. Details beyond the abstract are not available.

Closest papers by meaning

• Template based Graph Neural Network with Optimal Transport Distances (NeurIPS 2022 · similarity 0.90)
• OpenGSL: A Comprehensive Benchmark for Graph Structure Learning (NeurIPS 2023 · similarity 0.89)
• Outlier-Robust Gromov-Wasserstein for Graph Data (NeurIPS 2023 · similarity 0.89)
• Wasserstein Graph Distance Based on L1–Approximated Tree Edit Distance between Weisfeiler–Lehman Subtrees (AAAI 2023 · similarity 0.88)
• Neural Gaussian Similarity Modeling for Differential Graph Structure Learning (AAAI 2024 · similarity 0.88)
• Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks (NeurIPS 2024 · similarity 0.87)