FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989952597> ?p ?o ?g. }

• W2989952597 abstract "Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's Quadratic Assignment Problem (QAP). This paper presents a QAP network directly learning with the affinity matrix (equivalently the association graph) whereby the matching problem is translated into a constrained vertex classification task. The association graph is learned by an embedding network for vertex classification, followed by Sinkhorn normalization and a cross-entropy loss for end-to-end learning. We further improve the embedding model on association graph by introducing Sinkhorn based matching-aware constraint, as well as dummy nodes to deal with unequal sizes of graphs. To our best knowledge, this is one of the first network to directly learn with the general Lawler's QAP. In contrast, recent deep matching methods focus on the learning of node/edge features in two graphs respectively. We also show how to extend our network to hypergraph matching, and matching of multiple graphs. Experimental results on both synthetic graphs and real-world images show its effectiveness. For pure QAP tasks on synthetic data and QAPLIB benchmark, our method can perform competitively and even surpass state-of-the-art graph matching and QAP solvers with notable less time cost. We provide a project homepage at http://thinklab.sjtu.edu.cn/project/NGM/index.html." @default.
• W2989952597 created "2019-12-05" @default.
• W2989952597 creator A5019708391 @default.
• W2989952597 creator A5069477050 @default.
• W2989952597 creator A5087158377 @default.
• W2989952597 date "2019-11-25" @default.
• W2989952597 modified "2023-09-28" @default.
• W2989952597 title "Neural Graph Matching Network: Learning Lawler's Quadratic Assignment Problem with Extension to Hypergraph and Multiple-graph Matching" @default.
• W2989952597 cites W104184427 @default.
• W2989952597 cites W1503085769 @default.
• W2989952597 cites W1556382839 @default.
• W2989952597 cites W1587878450 @default.
• W2989952597 cites W1665115054 @default.
• W2989952597 cites W1686810756 @default.
• W2989952597 cites W1744214816 @default.
• W2989952597 cites W1901379498 @default.
• W2989952597 cites W1938890191 @default.
• W2989952597 cites W1980190773 @default.
• W2989952597 cites W1998840160 @default.
• W2989952597 cites W2005720384 @default.
• W2989952597 cites W2013603106 @default.
• W2989952597 cites W2048698391 @default.
• W2989952597 cites W2067417069 @default.
• W2989952597 cites W2068627296 @default.
• W2989952597 cites W2084512390 @default.
• W2989952597 cites W2085261163 @default.
• W2989952597 cites W2097784989 @default.
• W2989952597 cites W2099897767 @default.
• W2989952597 cites W2107855892 @default.
• W2989952597 cites W2110056533 @default.
• W2989952597 cites W2116341502 @default.
• W2989952597 cites W2118104180 @default.
• W2989952597 cites W2120091187 @default.
• W2989952597 cites W2120803586 @default.
• W2989952597 cites W2121225280 @default.
• W2989952597 cites W2126448214 @default.
• W2989952597 cites W2138910149 @default.
• W2989952597 cites W2142726150 @default.
• W2989952597 cites W2150760714 @default.
• W2989952597 cites W2151975094 @default.
• W2989952597 cites W2152953631 @default.
• W2989952597 cites W2159537329 @default.
• W2989952597 cites W2166820607 @default.
• W2989952597 cites W2189538311 @default.
• W2989952597 cites W2204257188 @default.
• W2989952597 cites W2255320195 @default.
• W2989952597 cites W2280269595 @default.
• W2989952597 cites W2343970360 @default.
• W2989952597 cites W2369976370 @default.
• W2989952597 cites W2419507445 @default.
• W2989952597 cites W2519887557 @default.
• W2989952597 cites W2535410496 @default.
• W2989952597 cites W2588249105 @default.
• W2989952597 cites W2607264901 @default.
• W2989952597 cites W2765375060 @default.
• W2989952597 cites W2768308213 @default.
• W2989952597 cites W2776160996 @default.
• W2989952597 cites W2799132636 @default.
• W2989952597 cites W2887603607 @default.
• W2989952597 cites W2889037294 @default.
• W2989952597 cites W2892880750 @default.
• W2989952597 cites W2895478406 @default.
• W2989952597 cites W2950697450 @default.
• W2989952597 cites W2963079738 @default.
• W2989952597 cites W2963284675 @default.
• W2989952597 cites W2963655172 @default.
• W2989952597 cites W2964121744 @default.
• W2989952597 cites W2964316651 @default.
• W2989952597 cites W2966720510 @default.
• W2989952597 cites W2978283152 @default.
• W2989952597 cites W2983178467 @default.
• W2989952597 cites W2992174520 @default.
• W2989952597 cites W2994872781 @default.
• W2989952597 cites W3019350928 @default.
• W2989952597 cites W3034659318 @default.
• W2989952597 cites W3035512722 @default.
• W2989952597 cites W3039701618 @default.
• W2989952597 cites W3047863327 @default.
• W2989952597 cites W3085990079 @default.
• W2989952597 cites W3099546855 @default.
• W2989952597 cites W3121235808 @default.
• W2989952597 cites W48175873 @default.
• W2989952597 cites W50270175 @default.
• W2989952597 cites W272982077 @default.
• W2989952597 doi "https://doi.org/10.48550/arxiv.1911.11308" @default.
• W2989952597 hasPublicationYear "2019" @default.
• W2989952597 type Work @default.
• W2989952597 sameAs 2989952597 @default.
• W2989952597 citedByCount "10" @default.
• W2989952597 countsByYear W29899525972020 @default.
• W2989952597 countsByYear W29899525972021 @default.
• W2989952597 countsByYear W29899525972022 @default.
• W2989952597 crossrefType "posted-content" @default.
• W2989952597 hasAuthorship W2989952597A5019708391 @default.
• W2989952597 hasAuthorship W2989952597A5069477050 @default.
• W2989952597 hasAuthorship W2989952597A5087158377 @default.
• W2989952597 hasBestOaLocation W29899525971 @default.
• W2989952597 hasConcept C105795698 @default.
• W2989952597 hasConcept C11413529 @default.
• W2989952597 hasConcept C114614502 @default.

• next