Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215770542> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3215770542 abstract "Computing latent representations for graph-structured data is an ubiquitous learning task in many industrial and academic applications ranging from molecule synthetization to social network analysis and recommender systems. Knowledge graphs are among the most popular and widely used data representations related to the Semantic Web. Next to structuring factual knowledge in a machine-readable format, knowledge graphs serve as the backbone of many artificial intelligence applications and allow the ingestion of context information into various learning algorithms. Graph neural networks attempt to encode graph structures in low-dimensional vector spaces via a message passing heuristic between neighboring nodes. Over the recent years, a multitude of different graph neural network architectures demonstrated ground-breaking performances in many learning tasks. In this work, we propose a strategy to map deep graph learning architectures for knowledge graph reasoning to neuromorphic architectures. Based on the insight that randomly initialized and untrained (i.e., frozen) graph neural networks are able to preserve local graph structures, we compose a frozen neural network with shallow knowledge graph embedding models. We experimentally show that already on conventional computing hardware, this leads to a significant speedup and memory reduction while maintaining a competitive performance level. Moreover, we extend the frozen architecture to spiking neural networks, introducing a novel, event-based and highly sparse knowledge graph embedding algorithm that is suitable for implementation in neuromorphic hardware." @default.
- W3215770542 created "2021-12-06" @default.
- W3215770542 creator A5002518694 @default.
- W3215770542 creator A5006443017 @default.
- W3215770542 creator A5063752112 @default.
- W3215770542 creator A5088656212 @default.
- W3215770542 date "2021-10-15" @default.
- W3215770542 modified "2023-09-26" @default.
- W3215770542 title "Learning Through Structure: Towards Deep Neuromorphic Knowledge Graph Embeddings" @default.
- W3215770542 cites W1498436455 @default.
- W3215770542 cites W1529533208 @default.
- W3215770542 cites W1604973310 @default.
- W3215770542 cites W2116341502 @default.
- W3215770542 cites W2247119764 @default.
- W3215770542 cites W2529004582 @default.
- W3215770542 cites W2604314403 @default.
- W3215770542 cites W2766447205 @default.
- W3215770542 cites W2783525259 @default.
- W3215770542 cites W2805197914 @default.
- W3215770542 cites W2900163261 @default.
- W3215770542 cites W2909081594 @default.
- W3215770542 cites W2919115771 @default.
- W3215770542 cites W2922002199 @default.
- W3215770542 cites W2945514530 @default.
- W3215770542 cites W2962946486 @default.
- W3215770542 cites W2964010909 @default.
- W3215770542 cites W3002185698 @default.
- W3215770542 cites W3089433719 @default.
- W3215770542 cites W3106615112 @default.
- W3215770542 cites W3126028740 @default.
- W3215770542 cites W3165706714 @default.
- W3215770542 cites W3171047464 @default.
- W3215770542 cites W3198760505 @default.
- W3215770542 cites W3200084004 @default.
- W3215770542 cites W3200675488 @default.
- W3215770542 doi "https://doi.org/10.1109/icnc52316.2021.9607968" @default.
- W3215770542 hasPublicationYear "2021" @default.
- W3215770542 type Work @default.
- W3215770542 sameAs 3215770542 @default.
- W3215770542 citedByCount "3" @default.
- W3215770542 countsByYear W32157705422022 @default.
- W3215770542 crossrefType "proceedings-article" @default.
- W3215770542 hasAuthorship W3215770542A5002518694 @default.
- W3215770542 hasAuthorship W3215770542A5006443017 @default.
- W3215770542 hasAuthorship W3215770542A5063752112 @default.
- W3215770542 hasAuthorship W3215770542A5088656212 @default.
- W3215770542 hasBestOaLocation W32157705422 @default.
- W3215770542 hasConcept C108583219 @default.
- W3215770542 hasConcept C119857082 @default.
- W3215770542 hasConcept C132525143 @default.
- W3215770542 hasConcept C151927369 @default.
- W3215770542 hasConcept C154945302 @default.
- W3215770542 hasConcept C173608175 @default.
- W3215770542 hasConcept C41008148 @default.
- W3215770542 hasConcept C41608201 @default.
- W3215770542 hasConcept C50644808 @default.
- W3215770542 hasConcept C68339613 @default.
- W3215770542 hasConcept C80444323 @default.
- W3215770542 hasConceptScore W3215770542C108583219 @default.
- W3215770542 hasConceptScore W3215770542C119857082 @default.
- W3215770542 hasConceptScore W3215770542C132525143 @default.
- W3215770542 hasConceptScore W3215770542C151927369 @default.
- W3215770542 hasConceptScore W3215770542C154945302 @default.
- W3215770542 hasConceptScore W3215770542C173608175 @default.
- W3215770542 hasConceptScore W3215770542C41008148 @default.
- W3215770542 hasConceptScore W3215770542C41608201 @default.
- W3215770542 hasConceptScore W3215770542C50644808 @default.
- W3215770542 hasConceptScore W3215770542C68339613 @default.
- W3215770542 hasConceptScore W3215770542C80444323 @default.
- W3215770542 hasFunder F4320323803 @default.
- W3215770542 hasLocation W32157705421 @default.
- W3215770542 hasLocation W32157705422 @default.
- W3215770542 hasOpenAccess W3215770542 @default.
- W3215770542 hasPrimaryLocation W32157705421 @default.
- W3215770542 hasRelatedWork W2922457425 @default.
- W3215770542 hasRelatedWork W3014300295 @default.
- W3215770542 hasRelatedWork W3164822677 @default.
- W3215770542 hasRelatedWork W4223943233 @default.
- W3215770542 hasRelatedWork W4225161397 @default.
- W3215770542 hasRelatedWork W4250304930 @default.
- W3215770542 hasRelatedWork W4309045103 @default.
- W3215770542 hasRelatedWork W4312200629 @default.
- W3215770542 hasRelatedWork W4360585206 @default.
- W3215770542 hasRelatedWork W4364306694 @default.
- W3215770542 isParatext "false" @default.
- W3215770542 isRetracted "false" @default.
- W3215770542 magId "3215770542" @default.
- W3215770542 workType "article" @default.