Wasserstein-based Graph Alignment

• URL: http://arxiv.org/abs/2003.06048v1
• Date: Thu, 12 Mar 2020 22:31:59 GMT
• Title: Wasserstein-based Graph Alignment
• Authors: Hermina Petric Maretic, Mireille El Gheche, Matthias Minder, Giovanni Chierchia, Pascal Frossard
• Abstract summary: 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.
• Score: 56.84964475441094
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose a novel method for comparing non-aligned graphs of different sizes, based on the Wasserstein distance between graph signal distributions induced by the respective graph Laplacian matrices. Specifically, 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. By integrating optimal transport in our graph comparison framework, we generate both a structurally-meaningful graph distance, and a signal transportation plan that models the structure of graph data. The resulting alignment problem is solved with stochastic gradient descent, where we use a novel Dykstra operator to ensure that the solution is a one-to-many (soft) assignment matrix. We demonstrate the performance of our novel framework on graph alignment and graph classification, and we show that our method leads to significant improvements with respect to the state-of-the-art algorithms for each of these tasks.

Related papers

• Robust Graph Matching Using An Unbalanced Hierarchical Optimal Transport Framework [30.05543844763625]
  We propose a novel and robust graph matching method based on an unbalanced hierarchical optimal transport framework. We make the first attempt to exploit cross-modal alignment in graph matching. Experiments on various graph matching tasks demonstrate the superiority and robustness of our method compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-10-18T16:16:53Z)
• Graph Mixup with Soft Alignments [49.61520432554505]
  We study graph data augmentation by mixup, which has been used successfully on images. We propose S-Mixup, a simple yet effective mixup method for graph classification by soft alignments.
  arXiv  Detail & Related papers  (2023-06-11T22:04:28Z)
• Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport [26.58964162799207]
  We propose SLOTAlign, an unsupervised graph alignment framework that jointly performs Structure Learning and Optimal Transport Alignment. We incorporate multi-view structure learning to enhance graph representation power and reduce the effect of structure and feature inconsistency inherited across graphs. The proposed SLOTAlign shows superior performance and strongest robustness over seven unsupervised graph alignment methods and five specialized KG alignment methods.
  arXiv  Detail & Related papers  (2023-01-30T08:41:36Z)
• FGOT: Graph Distances based on Filters and Optimal Transport [62.779521543654134]
  Graph comparison deals with identifying similarities and dissimilarities between graphs. A major obstacle is the unknown alignment of graphs, as well as the lack of accurate and inexpensive comparison metrics. In this work we introduce the filter graph distance approximation.
  arXiv  Detail & Related papers  (2021-09-09T17:43:07Z)
• Sparse Partial Least Squares for Coarse Noisy Graph Alignment [10.172041234280865]
  Graph signal processing (GSP) provides a powerful framework for analyzing signals arising in a variety of domains. We propose a novel regularized partial least squares method which both incorporates the observed graph structures and imposes sparsity in order to reflect the underlying block community structure.
  arXiv  Detail & Related papers  (2021-04-06T21:52:15Z)
• Some Algorithms on Exact, Approximate and Error-Tolerant Graph Matching [3.655021726150369]
  We present an extensive survey of various exact and inexact graph matching techniques. A category of graph matching algorithms is presented, which reduces the graph size by removing the less important nodes. We introduce a novel approach to measure graph similarity using geometric graphs.
  arXiv  Detail & Related papers  (2020-12-30T18:51:06Z)
• Multilayer Clustered Graph Learning [66.94201299553336]
  We use contrastive loss as a data fidelity term, in order to properly aggregate the observed layers into a representative graph. Experiments show that our method leads to a clustered clusters w.r.t. We learn a clustering algorithm for solving clustering problems.
  arXiv  Detail & Related papers  (2020-10-29T09:58:02Z)
• 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)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• Wasserstein Embedding for Graph Learning [33.90471037116372]
  Wasserstein Embedding for Graph Learning (WEGL) is a framework for embedding entire graphs in a vector space. We leverage new insights on defining similarity between graphs as a function of the similarity between their node embedding distributions. We evaluate our new graph embedding approach on various benchmark graph-property prediction tasks.
  arXiv  Detail & Related papers  (2020-06-16T18:23:00Z)

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.