Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375928204> ?p ?o ?g. }
- W4375928204 endingPage "1656" @default.
- W4375928204 startingPage "1643" @default.
- W4375928204 abstract "Graph embedding maps graph nodes to low-dimensional vectors, and is widely adopted in machine learning tasks. The increasing availability of billion-edge graphs underscores the importance of learning efficient and effective embeddings on large graphs, such as link prediction on Twitter with over one billion edges. Most existing graph embedding methods fall short of reaching high data scalability. In this paper, we present a general-purpose, distributed, information-centric random walk-based graph embedding framework, DistGER, which can scale to embed billion-edge graphs. DistGER incrementally computes information-centric random walks. It further leverages a multi-proximity-aware, streaming, parallel graph partitioning strategy, simultaneously achieving high local partition quality and excellent workload balancing across machines. DistGER also improves the distributed Skip-Gram learning model to generate node embeddings by optimizing the access locality, CPU throughput, and synchronization efficiency. Experiments on real-world graphs demonstrate that compared to state-of-the-art distributed graph embedding frameworks, including KnightKing, DistDGL, and Pytorch-BigGraph, DistGER exhibits 2.33×--129× acceleration, 45% reduction in cross-machines communication, and >10% effectiveness improvement in downstream tasks." @default.
- W4375928204 created "2023-05-10" @default.
- W4375928204 creator A5001085706 @default.
- W4375928204 creator A5002661071 @default.
- W4375928204 creator A5004937453 @default.
- W4375928204 creator A5009005101 @default.
- W4375928204 creator A5019024971 @default.
- W4375928204 creator A5048708699 @default.
- W4375928204 creator A5077949136 @default.
- W4375928204 creator A5086767017 @default.
- W4375928204 date "2023-03-01" @default.
- W4375928204 modified "2023-10-16" @default.
- W4375928204 title "Distributed Graph Embedding with Information-Oriented Random Walks" @default.
- W4375928204 cites W1482680420 @default.
- W4375928204 cites W1910515323 @default.
- W4375928204 cites W1971630691 @default.
- W4375928204 cites W1978555214 @default.
- W4375928204 cites W1982056505 @default.
- W4375928204 cites W1994616650 @default.
- W4375928204 cites W2003707464 @default.
- W4375928204 cites W2006023152 @default.
- W4375928204 cites W2008620264 @default.
- W4375928204 cites W2033314190 @default.
- W4375928204 cites W2045271686 @default.
- W4375928204 cites W2070232376 @default.
- W4375928204 cites W2101196063 @default.
- W4375928204 cites W2105543219 @default.
- W4375928204 cites W2149381887 @default.
- W4375928204 cites W2393319904 @default.
- W4375928204 cites W2604366058 @default.
- W4375928204 cites W2604942799 @default.
- W4375928204 cites W2604983939 @default.
- W4375928204 cites W2766865699 @default.
- W4375928204 cites W2788614083 @default.
- W4375928204 cites W2808867307 @default.
- W4375928204 cites W2889350994 @default.
- W4375928204 cites W2912516411 @default.
- W4375928204 cites W2948637333 @default.
- W4375928204 cites W2951479072 @default.
- W4375928204 cites W2962756421 @default.
- W4375928204 cites W2962836134 @default.
- W4375928204 cites W2963169753 @default.
- W4375928204 cites W2963224980 @default.
- W4375928204 cites W2963601856 @default.
- W4375928204 cites W2963707260 @default.
- W4375928204 cites W2966694634 @default.
- W4375928204 cites W2982231843 @default.
- W4375928204 cites W3007813770 @default.
- W4375928204 cites W3100330855 @default.
- W4375928204 cites W3103311102 @default.
- W4375928204 cites W3104097132 @default.
- W4375928204 cites W3105705953 @default.
- W4375928204 cites W3158520854 @default.
- W4375928204 cites W3159953606 @default.
- W4375928204 cites W3175440854 @default.
- W4375928204 cites W3207627052 @default.
- W4375928204 cites W4283314525 @default.
- W4375928204 cites W4289646353 @default.
- W4375928204 cites W4292718518 @default.
- W4375928204 cites W4293023446 @default.
- W4375928204 doi "https://doi.org/10.14778/3587136.3587140" @default.
- W4375928204 hasPublicationYear "2023" @default.
- W4375928204 type Work @default.
- W4375928204 citedByCount "0" @default.
- W4375928204 crossrefType "journal-article" @default.
- W4375928204 hasAuthorship W4375928204A5001085706 @default.
- W4375928204 hasAuthorship W4375928204A5002661071 @default.
- W4375928204 hasAuthorship W4375928204A5004937453 @default.
- W4375928204 hasAuthorship W4375928204A5009005101 @default.
- W4375928204 hasAuthorship W4375928204A5019024971 @default.
- W4375928204 hasAuthorship W4375928204A5048708699 @default.
- W4375928204 hasAuthorship W4375928204A5077949136 @default.
- W4375928204 hasAuthorship W4375928204A5086767017 @default.
- W4375928204 hasConcept C105795698 @default.
- W4375928204 hasConcept C114614502 @default.
- W4375928204 hasConcept C120314980 @default.
- W4375928204 hasConcept C121194460 @default.
- W4375928204 hasConcept C132525143 @default.
- W4375928204 hasConcept C138885662 @default.
- W4375928204 hasConcept C138959212 @default.
- W4375928204 hasConcept C154945302 @default.
- W4375928204 hasConcept C173608175 @default.
- W4375928204 hasConcept C187691185 @default.
- W4375928204 hasConcept C2524010 @default.
- W4375928204 hasConcept C2779808786 @default.
- W4375928204 hasConcept C33923547 @default.
- W4375928204 hasConcept C41008148 @default.
- W4375928204 hasConcept C41608201 @default.
- W4375928204 hasConcept C41895202 @default.
- W4375928204 hasConcept C42812 @default.
- W4375928204 hasConcept C48044578 @default.
- W4375928204 hasConcept C48903430 @default.
- W4375928204 hasConcept C75564084 @default.
- W4375928204 hasConcept C77088390 @default.
- W4375928204 hasConcept C80444323 @default.
- W4375928204 hasConceptScore W4375928204C105795698 @default.
- W4375928204 hasConceptScore W4375928204C114614502 @default.
- W4375928204 hasConceptScore W4375928204C120314980 @default.