Graph Matching Relaxations and Amortization for Supervised Graph Prediction

• URL: http://arxiv.org/abs/2609.15437v1
• Date: Mon, 14 Sep 2026 12:00:52 GMT
• Title: Graph Matching Relaxations and Amortization for Supervised Graph Prediction
• Abstract summary: End-to-end Supervised Graph Prediction (SGP) requires a permutation-invariant loss to compare predicted and target graphs with arbitrary node orderings.<n>We first study three Optimal Transport relaxations of this problem and show, theoretically and empirically, that the Gromov-Wasserstein (GW) objective is the most suitable for SGP.<n>To avoid solving the resulting inner optimization for every training example, we propose to amortize the graph matching (node alignment) problem.
• Score: 11.692215143424976
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end Supervised Graph Prediction (SGP) requires a permutation-invariant loss to compare predicted and target graphs with arbitrary node orderings. Such losses typically involve a costly graph-matching problem. We first study three Optimal Transport relaxations of this problem and show, theoretically and empirically, that the Gromov-Wasserstein (GW) objective is the most suitable for SGP. Then, to avoid solving the resulting inner optimization for every training example, we propose to amortize the graph matching (node alignment) problem. For each training sample, the loss function leverages a transport plan provided by a parametric matcher based on the differentiable Sinkhorn algorithm applied on empirical node distributions. The graph prediction module and the matcher are jointly learned. We showcase the efficiency of this approach on toy and real world SGP problems of increasing complexity including a novel Mass-spectra to Scaffold task that we introduce.

Related papers

• AGDN: Learning to Solve Traveling Salesman Problem with Anisotropic Graph Diffusion Network [50.69521065962045]
  We present the Anisotropic Graph Diffusion Network (AGDN), a new Graph Neural Network framework designed to solve the Traveling Salesman Problem (TSP)<n>Our method tackles two central difficulties: (1) the lack of informative topological prior in fully connected TSP graphs, and (2) losing connected nodes in the optimal solution after the commonly used graph sparsification techniques.<n>AGDN consistently outperforms existing methods while keeping time competitive.
  arXiv  Detail & Related papers  (2026-06-17T15:24:37Z)
• Differentiable Proximal Graph Matching [40.41380102260085]
  We introduce an algorithm for graph matching based on the proximal operator, referred to as differentiable proximal graph matching (DPGM) The whole algorithm can be considered as a differentiable map from the graph affinity matrix to the prediction of node correspondence. Numerical experiments show that PGM outperforms existing graph matching algorithms on diverse datasets.
  arXiv  Detail & Related papers  (2024-05-26T08:17:13Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• Gradient scarcity with Bilevel Optimization for Graph Learning [0.0]
  gradient scarcity occurs when learning graphs by minimizing a loss on a subset of nodes causes edges between unlabelled nodes that are far from labelled ones to receive zero gradients. We give a precise mathematical characterization of this phenomenon, and prove it also emerges in bilevel optimization. To alleviate this issue, we study several solutions: we propose to resort to latent graph learning using a Graph-to-Graph model (G2G), graph regularization to impose a prior structure on the graph, or optimizing on a larger graph than the original one with a reduced diameter.
  arXiv  Detail & Related papers  (2023-03-24T12:37:43Z)
• Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching [68.35685422301613]
  We propose a novel non-parametric subgraph matching framework, dubbed MatchExplainer, to explore explanatory subgraphs. It couples the target graph with other counterpart instances and identifies the most crucial joint substructure by minimizing the node corresponding-based distance. Experiments on synthetic and real-world datasets show the effectiveness of our MatchExplainer by outperforming all state-of-the-art parametric baselines with significant margins.
  arXiv  Detail & Related papers  (2023-01-07T05:14:45Z)
• Deep graph matching meets mixed-integer linear programming: Relax at your own risk ? [8.05409526074409]
  We propose an approach integrating a MILP formulation of the graph matching problem. Similar approaches are derived by releasing the optimal guarantee of the graph matching solver and by introducing a quality level. Our experimental evaluation gives several theoretical insights and guides the direction of deep graph matching methods.
  arXiv  Detail & Related papers  (2021-08-01T08:29:55Z)
• Line Graph Neural Networks for Link Prediction [71.00689542259052]
  We consider the graph link prediction task, which is a classic graph analytical problem with many real-world applications. In this formalism, a link prediction problem is converted to a graph classification task. We propose to seek a radically different and novel path by making use of the line graphs in graph theory. In particular, each node in a line graph corresponds to a unique edge in the original graph. Therefore, link prediction problems in the original graph can be equivalently solved as a node classification problem in its corresponding line graph, instead of a graph classification task.
  arXiv  Detail & Related papers  (2020-10-20T05:54:31Z)
• A Generative Graph Method to Solve the Travelling Salesman Problem [1.552282932199974]
  We propose to use the novel Graph Learning Network (GLN), a generative approach, to approximately solve the Travelling Salesman Problem (TSP) GLN model learns directly the pattern of TSP instances as training dataset, encodes the graph properties, and merge the different node embeddings to output node-to-node an optimal tour.
  arXiv  Detail & Related papers  (2020-07-09T17:23:55Z)
• Wasserstein-based Graph Alignment [56.84964475441094]
  We cast a new formulation for the one-to-many graph alignment problem, which aims at matching a node in the smaller graph with one or more nodes in the larger graph. We show that our method leads to significant improvements with respect to the state-of-the-art algorithms for each of these tasks.
  arXiv  Detail & Related papers  (2020-03-12T22:31:59Z)
• Graph Ordering: Towards the Optimal by Learning [69.72656588714155]
  Graph representation learning has achieved a remarkable success in many graph-based applications, such as node classification, prediction, and community detection. However, for some kind of graph applications, such as graph compression and edge partition, it is very hard to reduce them to some graph representation learning tasks. In this paper, we propose to attack the graph ordering problem behind such applications by a novel learning approach.
  arXiv  Detail & Related papers  (2020-01-18T09:14:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.