Universe Points Representation Learning for Partial Multi-Graph Matching

• URL: http://arxiv.org/abs/2212.00780v1
• Date: Thu, 1 Dec 2022 18:58:26 GMT
• Title: Universe Points Representation Learning for Partial Multi-Graph Matching
• Authors: Zhakshylyk Nurlanov, Frank R. Schmidt, Florian Bernard
• Abstract summary: We study the more general partial matching problem with multi-graph cycle consistency guarantees. We propose a novel data-driven method for partial multi-graph matching, which uses an object-to-universe formulation and learns latent representations of abstract universe points.
• Score: 17.46692880231195
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider a full two-graph matching setting. In this work, we study the more general partial matching problem with multi-graph cycle consistency guarantees. Building on a recent progress in deep learning on graphs, we propose a novel data-driven method (URL) for partial multi-graph matching, which uses an object-to-universe formulation and learns latent representations of abstract universe points. The proposed approach advances the state of the art in semantic keypoint matching problem, evaluated on Pascal VOC, CUB, and Willow datasets. Moreover, the set of controlled experiments on a synthetic graph matching dataset demonstrates the scalability of our method to graphs with large number of nodes and its robustness to high partiality.

Related papers

• Learning Universe Model for Partial Matching Networks over Multiple Graphs [78.85255014094223]
  We develop a universe matching scheme for partial matching of two or multiple graphs. The subtle logic for inlier matching and outlier detection can be clearly modeled. This is the first deep learning network that can cope with two-graph matching, multiple-graph matching, online matching, and mixture graph matching simultaneously.
  arXiv  Detail & Related papers  (2022-10-19T08:34:00Z)
• High-order Multi-view Clustering for Generic Data [15.764819403555512]
  Graph-based multi-view clustering has achieved better performance than most non-graph approaches. We introduce an approach called high-order multi-view clustering (HMvC) to explore the topology structure information of generic data.
  arXiv  Detail & Related papers  (2022-09-22T07:49:38Z)
• All the World's a (Hyper)Graph: A Data Drama [55.144729234861316]
  Hyperbard is a dataset of diverse data representations from Shakespeare's plays. Our representations range from simple graphs capturing character co-occurrence in single scenes to hypergraphs encoding complex communication settings. As an homage to our data source, and asserting that science can also be art, we present all our points in the form of a play.
  arXiv  Detail & Related papers  (2022-06-16T14:51:28Z)
• Multi-view Contrastive Graph Clustering [12.463334005083379]
  We propose a generic framework to cluster multi-view attributed graph data. Inspired by the success of contrastive learning, we propose multi-view contrastive graph clustering (MCGC) method. Our simple approach outperforms existing deep learning-based methods.
  arXiv  Detail & Related papers  (2021-10-22T15:22:42Z)
• Edge but not Least: Cross-View Graph Pooling [76.71497833616024]
  This paper presents a cross-view graph pooling (Co-Pooling) method to better exploit crucial graph structure information. Through cross-view interaction, edge-view pooling and node-view pooling seamlessly reinforce each other to learn more informative graph-level representations.
  arXiv  Detail & Related papers  (2021-09-24T08:01:23Z)
• Joint Graph Learning and Matching for Semantic Feature Correspondence [69.71998282148762]
  We propose a joint emphgraph learning and matching network, named GLAM, to explore reliable graph structures for boosting graph matching. The proposed method is evaluated on three popular visual matching benchmarks (Pascal VOC, Willow Object and SPair-71k) It outperforms previous state-of-the-art graph matching methods by significant margins on all benchmarks.
  arXiv  Detail & Related papers  (2021-09-01T08:24:02Z)
• 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)
• Accurate Learning of Graph Representations with Graph Multiset Pooling [45.72542969364438]
  We propose a Graph Multiset Transformer (GMT) that captures the interaction between nodes according to their structural dependencies. Our experimental results show that GMT significantly outperforms state-of-the-art graph pooling methods on graph classification benchmarks.
  arXiv  Detail & Related papers  (2021-02-23T07:45:58Z)
• Deep Reinforcement Learning of Graph Matching [63.469961545293756]
  Graph matching (GM) under node and pairwise constraints has been a building block in areas from optimization to computer vision. We present a reinforcement learning solver for GM i.e. RGM that seeks the node correspondence between pairwise graphs. Our method differs from the previous deep graph matching model in the sense that they are focused on the front-end feature extraction and affinity function learning.
  arXiv  Detail & Related papers  (2020-12-16T13:48:48Z)
• Multi-view Graph Learning by Joint Modeling of Consistency and Inconsistency [65.76554214664101]
  Graph learning has emerged as a promising technique for multi-view clustering with its ability to learn a unified and robust graph from multiple views. We propose a new multi-view graph learning framework, which for the first time simultaneously models multi-view consistency and multi-view inconsistency in a unified objective function. Experiments on twelve multi-view datasets have demonstrated the robustness and efficiency of the proposed approach.
  arXiv  Detail & Related papers  (2020-08-24T06:11:29Z)

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.