FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3107500918> ?p ?o ?g. }

• W3107500918 endingPage "4269" @default.
• W3107500918 startingPage "4257" @default.
• W3107500918 abstract "Graph Neural Networks (GNNs) have led to state-of-the-art performance on a variety of machine learning tasks such as recommendation, node classification and link prediction. Graph neural network models generate node embeddings by merging nodes features with the aggregated neighboring nodes information. Most existing GNN models exploit a single type of aggregator (e.g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node. However, using only a single type of aggregator is difficult to capture the different aspects of neighboring information and the simple addition or concatenation update methods limit the expressive capability of GNNs. Not only that, existing supervised or semi-supervised GNN models are trained based on the loss function of the node label, which leads to the neglect of graph structure information. In this paper, we propose a novel graph neural network architecture, Graph Attention & Interaction Network (GAIN), for inductive learning on graphs. Unlike the previous GNN models that only utilize a single type of aggregation method, we use multiple types of aggregators to gather neighboring information in different aspects and integrate the outputs of these aggregators through the aggregator-level attention mechanism. Furthermore, we design a graph regularized loss to better capture the topological relationship of the nodes in the graph. Additionally, we first present the concept of graph feature interaction and propose a vector-wise explicit feature interaction mechanism to update the node embeddings. We conduct comprehensive experiments on two node-classification benchmarks and a real-world financial news dataset. The experiments demonstrate our GAIN model outperforms current state-of-the-art performances on all the tasks." @default.
• W3107500918 created "2020-12-07" @default.
• W3107500918 creator A5029446856 @default.
• W3107500918 creator A5041506088 @default.
• W3107500918 creator A5042785211 @default.
• W3107500918 creator A5053537544 @default.
• W3107500918 date "2022-09-01" @default.
• W3107500918 modified "2023-10-15" @default.
• W3107500918 title "GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning Over Large-Scale Graphs" @default.
• W3107500918 cites W1501856433 @default.
• W3107500918 cites W2101491865 @default.
• W3107500918 cites W2116341502 @default.
• W3107500918 cites W2139906443 @default.
• W3107500918 cites W2158787690 @default.
• W3107500918 cites W2295739661 @default.
• W3107500918 cites W2393319904 @default.
• W3107500918 cites W2475334473 @default.
• W3107500918 cites W2517540742 @default.
• W3107500918 cites W2562607067 @default.
• W3107500918 cites W2604662567 @default.
• W3107500918 cites W2612872092 @default.
• W3107500918 cites W2735272571 @default.
• W3107500918 cites W2793768763 @default.
• W3107500918 cites W2808490894 @default.
• W3107500918 cites W2945827377 @default.
• W3107500918 cites W2962756421 @default.
• W3107500918 cites W2963415211 @default.
• W3107500918 cites W2963512530 @default.
• W3107500918 cites W2964182926 @default.
• W3107500918 cites W3100848837 @default.
• W3107500918 cites W3101707147 @default.
• W3107500918 cites W3103720336 @default.
• W3107500918 cites W3105705953 @default.
• W3107500918 cites W4210257598 @default.
• W3107500918 doi "https://doi.org/10.1109/tkde.2020.3036212" @default.
• W3107500918 hasPublicationYear "2022" @default.
• W3107500918 type Work @default.
• W3107500918 sameAs 3107500918 @default.
• W3107500918 citedByCount "6" @default.
• W3107500918 countsByYear W31075009182022 @default.
• W3107500918 countsByYear W31075009182023 @default.
• W3107500918 crossrefType "journal-article" @default.
• W3107500918 hasAuthorship W3107500918A5029446856 @default.
• W3107500918 hasAuthorship W3107500918A5041506088 @default.
• W3107500918 hasAuthorship W3107500918A5042785211 @default.
• W3107500918 hasAuthorship W3107500918A5053537544 @default.
• W3107500918 hasConcept C111919701 @default.
• W3107500918 hasConcept C119857082 @default.
• W3107500918 hasConcept C124101348 @default.
• W3107500918 hasConcept C132525143 @default.
• W3107500918 hasConcept C154945302 @default.
• W3107500918 hasConcept C180505990 @default.
• W3107500918 hasConcept C2993807640 @default.
• W3107500918 hasConcept C41008148 @default.
• W3107500918 hasConcept C59404180 @default.
• W3107500918 hasConcept C70437156 @default.
• W3107500918 hasConcept C80444323 @default.
• W3107500918 hasConcept C83665646 @default.
• W3107500918 hasConceptScore W3107500918C111919701 @default.
• W3107500918 hasConceptScore W3107500918C119857082 @default.
• W3107500918 hasConceptScore W3107500918C124101348 @default.
• W3107500918 hasConceptScore W3107500918C132525143 @default.
• W3107500918 hasConceptScore W3107500918C154945302 @default.
• W3107500918 hasConceptScore W3107500918C180505990 @default.
• W3107500918 hasConceptScore W3107500918C2993807640 @default.
• W3107500918 hasConceptScore W3107500918C41008148 @default.
• W3107500918 hasConceptScore W3107500918C59404180 @default.
• W3107500918 hasConceptScore W3107500918C70437156 @default.
• W3107500918 hasConceptScore W3107500918C80444323 @default.
• W3107500918 hasConceptScore W3107500918C83665646 @default.
• W3107500918 hasFunder F4320321001 @default.
• W3107500918 hasFunder F4320334009 @default.
• W3107500918 hasIssue "9" @default.
• W3107500918 hasLocation W31075009181 @default.
• W3107500918 hasOpenAccess W3107500918 @default.
• W3107500918 hasPrimaryLocation W31075009181 @default.
• W3107500918 hasRelatedWork W2910744507 @default.
• W3107500918 hasRelatedWork W2914959431 @default.
• W3107500918 hasRelatedWork W2942587884 @default.
• W3107500918 hasRelatedWork W2944724518 @default.
• W3107500918 hasRelatedWork W3087493185 @default.
• W3107500918 hasRelatedWork W3093454656 @default.
• W3107500918 hasRelatedWork W3094685828 @default.
• W3107500918 hasRelatedWork W3145941582 @default.
• W3107500918 hasRelatedWork W3183761761 @default.
• W3107500918 hasRelatedWork W4307933185 @default.
• W3107500918 hasVolume "34" @default.
• W3107500918 isParatext "false" @default.
• W3107500918 isRetracted "false" @default.
• W3107500918 magId "3107500918" @default.
• W3107500918 workType "article" @default.