FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2107793528> ?p ?o ?g. }

• W2107793528 endingPage "3796" @default.
• W2107793528 startingPage "3783" @default.
• W2107793528 abstract "Classification on structure data, such as graphs, has drawn wide interest in recent years. Due to the lack of explicit features to represent graphs for training classification models, extensive studies have been focused on extracting the most discriminative subgraphs features from the training graph dataset to transfer graphs into vector data. However, such filter-based methods suffer from two major disadvantages: (1) the subgraph feature selection is separated from the model learning process, so the selected most discriminative subgraphs may not best fit the subsequent learning model, resulting in deteriorated classification results; (2) all these methods rely on users to specify the number of subgraph features K, and suboptimally specified K values often result in significantly reduced classification accuracy.In this paper, we propose a new graph classification paradigm which overcomes the above disadvantages by formulating subgraph feature selection as learning a K-dimensional feature space from an implicit and large subgraph space, with the optimal K value being automatically determined. To achieve the goal, we propose a regularized loss minimization-driven (RLMD) feature selection method for graph classification. RLMD integrates subgraph selection and model learning into a unified framework to find discriminative subgraphs with guaranteed minimum loss w.r.t. the objective function. To automatically determine the optimal number of subgraphs K from the exponentially large subgraph space, an effective elastic net and a subgradient method are proposed to derive the stopping criterion, so that K can be automatically obtained once RLMD converges. The proposed RLMD method enjoys gratifying property including proved convergence and applicability to various loss functions. Experimental results on real-life graph datasets demonstrate significant performance gain. HighlightsOur algorithm selects the optimal subgaphs for graph classification.We generalize the column generation technique of gBoost for graph classification.We use the elastic net to produce sparse and robust solutions for subgraph selection.We derive an effective pruning rule for search space reduction.We demonstrate the effectiveness of our algorithm." @default.
• W2107793528 created "2016-06-24" @default.
• W2107793528 creator A5007475662 @default.
• W2107793528 creator A5008056593 @default.
• W2107793528 creator A5059227406 @default.
• W2107793528 creator A5074852078 @default.
• W2107793528 creator A5084641325 @default.
• W2107793528 date "2015-11-01" @default.
• W2107793528 modified "2023-09-24" @default.
• W2107793528 title "Finding the best not the most: regularized loss minimization subgraph selection for graph classification" @default.
• W2107793528 cites W1524882660 @default.
• W2107793528 cites W1578080815 @default.
• W2107793528 cites W1971039378 @default.
• W2107793528 cites W1973848216 @default.
• W2107793528 cites W1974099839 @default.
• W2107793528 cites W2007240678 @default.
• W2107793528 cites W2007477772 @default.
• W2107793528 cites W2015342278 @default.
• W2107793528 cites W2016440973 @default.
• W2107793528 cites W2018245790 @default.
• W2107793528 cites W2099179622 @default.
• W2107793528 cites W2102039273 @default.
• W2107793528 cites W2108718322 @default.
• W2107793528 cites W2112737239 @default.
• W2107793528 cites W2113014179 @default.
• W2107793528 cites W2114062029 @default.
• W2107793528 cites W2122825543 @default.
• W2107793528 cites W2135725275 @default.
• W2107793528 cites W2137609262 @default.
• W2107793528 cites W2145388307 @default.
• W2107793528 cites W2148611932 @default.
• W2107793528 cites W2161723275 @default.
• W2107793528 cites W2164064742 @default.
• W2107793528 cites W2164281374 @default.
• W2107793528 cites W2168901348 @default.
• W2107793528 cites W2169847772 @default.
• W2107793528 cites W2185303849 @default.
• W2107793528 cites W2199139913 @default.
• W2107793528 cites W4232932184 @default.
• W2107793528 cites W817531966 @default.
• W2107793528 doi "https://doi.org/10.1016/j.patcog.2015.05.019" @default.
• W2107793528 hasPublicationYear "2015" @default.
• W2107793528 type Work @default.
• W2107793528 sameAs 2107793528 @default.
• W2107793528 citedByCount "34" @default.
• W2107793528 countsByYear W21077935282016 @default.
• W2107793528 countsByYear W21077935282017 @default.
• W2107793528 countsByYear W21077935282018 @default.
• W2107793528 countsByYear W21077935282019 @default.
• W2107793528 countsByYear W21077935282020 @default.
• W2107793528 countsByYear W21077935282021 @default.
• W2107793528 countsByYear W21077935282022 @default.
• W2107793528 crossrefType "journal-article" @default.
• W2107793528 hasAuthorship W2107793528A5007475662 @default.
• W2107793528 hasAuthorship W2107793528A5008056593 @default.
• W2107793528 hasAuthorship W2107793528A5059227406 @default.
• W2107793528 hasAuthorship W2107793528A5074852078 @default.
• W2107793528 hasAuthorship W2107793528A5084641325 @default.
• W2107793528 hasBestOaLocation W21077935282 @default.
• W2107793528 hasConcept C11413529 @default.
• W2107793528 hasConcept C114614502 @default.
• W2107793528 hasConcept C126255220 @default.
• W2107793528 hasConcept C132525143 @default.
• W2107793528 hasConcept C147764199 @default.
• W2107793528 hasConcept C153180895 @default.
• W2107793528 hasConcept C154945302 @default.
• W2107793528 hasConcept C191241153 @default.
• W2107793528 hasConcept C203776342 @default.
• W2107793528 hasConcept C22149727 @default.
• W2107793528 hasConcept C33923547 @default.
• W2107793528 hasConcept C41008148 @default.
• W2107793528 hasConcept C81917197 @default.
• W2107793528 hasConceptScore W2107793528C11413529 @default.
• W2107793528 hasConceptScore W2107793528C114614502 @default.
• W2107793528 hasConceptScore W2107793528C126255220 @default.
• W2107793528 hasConceptScore W2107793528C132525143 @default.
• W2107793528 hasConceptScore W2107793528C147764199 @default.
• W2107793528 hasConceptScore W2107793528C153180895 @default.
• W2107793528 hasConceptScore W2107793528C154945302 @default.
• W2107793528 hasConceptScore W2107793528C191241153 @default.
• W2107793528 hasConceptScore W2107793528C203776342 @default.
• W2107793528 hasConceptScore W2107793528C22149727 @default.
• W2107793528 hasConceptScore W2107793528C33923547 @default.
• W2107793528 hasConceptScore W2107793528C41008148 @default.
• W2107793528 hasConceptScore W2107793528C81917197 @default.
• W2107793528 hasIssue "11" @default.
• W2107793528 hasLocation W21077935281 @default.
• W2107793528 hasLocation W21077935282 @default.
• W2107793528 hasOpenAccess W2107793528 @default.
• W2107793528 hasPrimaryLocation W21077935281 @default.
• W2107793528 hasRelatedWork W1536220138 @default.
• W2107793528 hasRelatedWork W1922019929 @default.
• W2107793528 hasRelatedWork W1978042415 @default.
• W2107793528 hasRelatedWork W2037587960 @default.
• W2107793528 hasRelatedWork W2098278999 @default.
• W2107793528 hasRelatedWork W2146066930 @default.
• W2107793528 hasRelatedWork W2147229463 @default.
• W2107793528 hasRelatedWork W3086542228 @default.

• next