Hypergraph Neural Networks for Hypergraph Matching
Hypergraph matching is a useful tool to find feature correspondence by considering higher-order structural information. Recently, the employment of deep learning has made great progress in the matching of graphs, suggesting its potential for hypergraphs. Hence, in this paper, we present the first, to our best knowledge, unified hypergraph neural network (HNN) solution for hypergraph matching. Specifically, given two hypergraphs to be matched, we first construct an association hypergraph over them and convert the hypergraph matching problem into a node classification problem on the association hypergraph. Then, we design a novel hypergraph neural network to effectively solve the node classification problem. Being end-to-end trainable, our proposed method, named HNN-HM, jointly learns all its components with improved optimization. For evaluation, HNN-HM is tested on various benchmarks and shows a clear advantage over state-of-the-arts.
Code (1)
Tasks
Graph MatchingHypergraph MatchingNode ClassificationSimilar Papers 제목 키워드 기반
Hypergraph-Aided Task-Resource Matching for Maximizing Value of Task Completion in Collaborative IoT Systems
With the growing scale and intrinsic heterogeneity of Internet of Things (IoT) systems, distributed device collaboration becomes essential for effective task completion by dynamically utilizing limited communication and …
Hypergraph MatchingLearning Low Degree Hypergraphs
We study the problem of learning a hypergraph via edge detecting queries. In this problem, a learner queries subsets of vertices of a hidden hypergraph and observes whether these subsets contain an edge or not. In genera…
Firm-worker hypergraphs
A firm-worker hypergraph consists of edges in which each edge joins a firm and its possible employees. We show that a stable matching exists in both many-to-one matching with transferable utilities and discrete many-to-o…
CURSOR: Scalable Mixed-Order Hypergraph Matching with CUR Decomposition
To achieve greater accuracy, hypergraph matching algorithms require exponential increases in computational resources. Recent kd-tree-based approximate nearest neighbor (ANN) methods, despite the sparsity of their compati…
Graph MatchingHypergraph MatchingTensor DecompositionAn Efficient Multilinear Optimization Framework for Hypergraph Matching
Hypergraph matching has recently become a popular approach for solving correspondence problems in computer vision as it allows to integrate higher-order geometric information. Hypergraph matching can be formulated as a t…
Hypergraph Matching