FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108706836> ?p ?o ?g. }

• W3108706836 abstract "Graph neural networks (GNNs) are widely used in the applications based on graph structured data, such as node classification and link prediction. However, GNNs are often used as a black-box tool and rarely get in-depth investigated regarding whether they fit certain applications that may have various properties. A recently proposed technique distance encoding (DE) (Li et al. 2020) magically makes GNNs work well in many applications, including node classification and link prediction. The theory provided in (Li et al. 2020) supports DE by proving that DE improves the representation power of GNNs. However, it is not obvious how the theory assists the applications accordingly. Here, we revisit GNNs and DE from a more practical point of view. We want to explain how DE makes GNNs fit for node classification and link prediction. Specifically, for link prediction, DE can be viewed as a way to establish correlations between a pair of node representations. For node classification, the problem becomes more complicated as different classification tasks may hold node labels that indicate different physical meanings. We focus on the most widely-considered node classification scenarios and categorize the node labels into two types, community type and structure type, and then analyze different mechanisms that GNNs adopt to predict these two types of labels. We also run extensive experiments to compare eight different configurations of GNNs paired with DE to predict node labels over eight real-world graphs. The results demonstrate the uniform effectiveness of DE to predict structure-type labels. Lastly, we reach three pieces of conclusions on how to use GNNs and DE properly in tasks of node classification." @default.
• W3108706836 created "2020-12-07" @default.
• W3108706836 creator A5001319317 @default.
• W3108706836 creator A5004119013 @default.
• W3108706836 creator A5037159442 @default.
• W3108706836 date "2020-11-22" @default.
• W3108706836 modified "2023-09-27" @default.
• W3108706836 title "Revisit graph neural networks and distance encoding in a practical view." @default.
• W3108706836 cites W2057685268 @default.
• W3108706836 cites W2107559689 @default.
• W3108706836 cites W2116341502 @default.
• W3108706836 cites W2153959628 @default.
• W3108706836 cites W2607500032 @default.
• W3108706836 cites W2624431344 @default.
• W3108706836 cites W2805516822 @default.
• W3108706836 cites W2900763475 @default.
• W3108706836 cites W2916106175 @default.
• W3108706836 cites W2945328865 @default.
• W3108706836 cites W2962756421 @default.
• W3108706836 cites W2962767366 @default.
• W3108706836 cites W2963460103 @default.
• W3108706836 cites W2963757395 @default.
• W3108706836 cites W2963858333 @default.
• W3108706836 cites W2964015378 @default.
• W3108706836 cites W2964121744 @default.
• W3108706836 cites W2964124573 @default.
• W3108706836 cites W2970453599 @default.
• W3108706836 cites W2970843311 @default.
• W3108706836 cites W2975966238 @default.
• W3108706836 cites W2995509042 @default.
• W3108706836 cites W2996491671 @default.
• W3108706836 cites W3030661718 @default.
• W3108706836 cites W3035419610 @default.
• W3108706836 cites W3036490401 @default.
• W3108706836 cites W3040043284 @default.
• W3108706836 cites W3081636763 @default.
• W3108706836 cites W3090016979 @default.
• W3108706836 cites W3093814892 @default.
• W3108706836 cites W3094003325 @default.
• W3108706836 cites W3097264851 @default.
• W3108706836 cites W67413104 @default.
• W3108706836 hasPublicationYear "2020" @default.
• W3108706836 type Work @default.
• W3108706836 sameAs 3108706836 @default.
• W3108706836 citedByCount "1" @default.
• W3108706836 countsByYear W31087068362021 @default.
• W3108706836 crossrefType "posted-content" @default.
• W3108706836 hasAuthorship W3108706836A5001319317 @default.
• W3108706836 hasAuthorship W3108706836A5004119013 @default.
• W3108706836 hasAuthorship W3108706836A5037159442 @default.
• W3108706836 hasConcept C119857082 @default.
• W3108706836 hasConcept C124101348 @default.
• W3108706836 hasConcept C127413603 @default.
• W3108706836 hasConcept C132525143 @default.
• W3108706836 hasConcept C154945302 @default.
• W3108706836 hasConcept C2778753846 @default.
• W3108706836 hasConcept C31258907 @default.
• W3108706836 hasConcept C41008148 @default.
• W3108706836 hasConcept C62611344 @default.
• W3108706836 hasConcept C66938386 @default.
• W3108706836 hasConcept C80444323 @default.
• W3108706836 hasConcept C94124525 @default.
• W3108706836 hasConceptScore W3108706836C119857082 @default.
• W3108706836 hasConceptScore W3108706836C124101348 @default.
• W3108706836 hasConceptScore W3108706836C127413603 @default.
• W3108706836 hasConceptScore W3108706836C132525143 @default.
• W3108706836 hasConceptScore W3108706836C154945302 @default.
• W3108706836 hasConceptScore W3108706836C2778753846 @default.
• W3108706836 hasConceptScore W3108706836C31258907 @default.
• W3108706836 hasConceptScore W3108706836C41008148 @default.
• W3108706836 hasConceptScore W3108706836C62611344 @default.
• W3108706836 hasConceptScore W3108706836C66938386 @default.
• W3108706836 hasConceptScore W3108706836C80444323 @default.
• W3108706836 hasConceptScore W3108706836C94124525 @default.
• W3108706836 hasLocation W31087068361 @default.
• W3108706836 hasOpenAccess W3108706836 @default.
• W3108706836 hasPrimaryLocation W31087068361 @default.
• W3108706836 hasRelatedWork W2894175828 @default.
• W3108706836 hasRelatedWork W2912323206 @default.
• W3108706836 hasRelatedWork W2972317931 @default.
• W3108706836 hasRelatedWork W2981275410 @default.
• W3108706836 hasRelatedWork W2982166258 @default.
• W3108706836 hasRelatedWork W2987673972 @default.
• W3108706836 hasRelatedWork W3003345311 @default.
• W3108706836 hasRelatedWork W3081636763 @default.
• W3108706836 hasRelatedWork W3094003325 @default.
• W3108706836 hasRelatedWork W3095454939 @default.
• W3108706836 hasRelatedWork W3101198795 @default.
• W3108706836 hasRelatedWork W3103472792 @default.
• W3108706836 hasRelatedWork W3133953674 @default.
• W3108706836 hasRelatedWork W3153206160 @default.
• W3108706836 hasRelatedWork W3172527071 @default.
• W3108706836 hasRelatedWork W3176894340 @default.
• W3108706836 hasRelatedWork W3178081756 @default.
• W3108706836 hasRelatedWork W3200726313 @default.
• W3108706836 hasRelatedWork W3201628596 @default.
• W3108706836 hasRelatedWork W3204410986 @default.
• W3108706836 isParatext "false" @default.
• W3108706836 isRetracted "false" @default.
• W3108706836 magId "3108706836" @default.

• next