Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384705463> ?p ?o ?g. }
- W4384705463 abstract "Streaming tensor factorization is an effective tool for unsupervised analysis of time-evolving sparse data, which emerge in many critical domains such as cybersecurity and trend analysis. In contrast to traditional tensors, time-evolving tensors demonstrate extreme sparsity and sparsity variation over time, resulting in irregular memory access and inefficient use of parallel computing resources. Additionally, due to the prohibitive cost of dynamically generating compressed sparse tensor formats, the state-of-the-art approaches process streaming tensors in a raw form that fails to capture data locality and suffers from high synchronization cost. To address these challenges, we propose a new dynamic tensor linearization framework that quickly encodes streaming multi-dimensional data on-the-fly in a compact representation, which has substantially lower memory usage and higher data reuse and parallelism than the original raw data. This is achieved by using a spatial sketching algorithm that keeps all incoming nonzero elements but remaps them into a tensor sketch with considerably reduced multi-dimensional image space. Moreover, we present a dynamic time slicing mechanism that uses variable-width time slices (instead of the traditional fixed-width) to balance the frequency of factor updates and the utilization of computing resources. We demonstrate the efficacy of our framework by accelerating two high-performance streaming tensor algorithms, namely, CP-stream and spCP-stream, and significantly improve their performance for a range of real-world streaming tensors. On a modern 56-core CPU, our framework achieves 10.3 − 11× and 6.4 − 7.2× geometric-mean speedup for the CP-stream and spCP-stream algorithms, respectively." @default.
- W4384705463 created "2023-07-20" @default.
- W4384705463 creator A5018257269 @default.
- W4384705463 creator A5026593207 @default.
- W4384705463 creator A5031307529 @default.
- W4384705463 creator A5047885427 @default.
- W4384705463 creator A5049815529 @default.
- W4384705463 creator A5065069377 @default.
- W4384705463 creator A5066195314 @default.
- W4384705463 creator A5090060327 @default.
- W4384705463 date "2023-05-01" @default.
- W4384705463 modified "2023-09-26" @default.
- W4384705463 title "Dynamic Tensor Linearization and Time Slicing for Efficient Factorization of Infinite Data Streams" @default.
- W4384705463 cites W1511885491 @default.
- W4384705463 cites W1963826206 @default.
- W4384705463 cites W2000215628 @default.
- W4384705463 cites W2003571173 @default.
- W4384705463 cites W2024165284 @default.
- W4384705463 cites W2024356620 @default.
- W4384705463 cites W2079487069 @default.
- W4384705463 cites W2098171862 @default.
- W4384705463 cites W2127226421 @default.
- W4384705463 cites W2245094585 @default.
- W4384705463 cites W2262232454 @default.
- W4384705463 cites W2274757334 @default.
- W4384705463 cites W2481767403 @default.
- W4384705463 cites W2482092413 @default.
- W4384705463 cites W2616934551 @default.
- W4384705463 cites W2800391958 @default.
- W4384705463 cites W2902289997 @default.
- W4384705463 cites W2902783593 @default.
- W4384705463 cites W2907662941 @default.
- W4384705463 cites W2950423973 @default.
- W4384705463 cites W2951178714 @default.
- W4384705463 cites W2964103059 @default.
- W4384705463 cites W2986686333 @default.
- W4384705463 cites W3005990752 @default.
- W4384705463 cites W3012523953 @default.
- W4384705463 cites W3037313756 @default.
- W4384705463 cites W3129727110 @default.
- W4384705463 cites W3163255915 @default.
- W4384705463 cites W3164929383 @default.
- W4384705463 cites W3174250345 @default.
- W4384705463 cites W3174786754 @default.
- W4384705463 cites W3210814098 @default.
- W4384705463 cites W4200452998 @default.
- W4384705463 cites W4282975603 @default.
- W4384705463 doi "https://doi.org/10.1109/ipdps54959.2023.00048" @default.
- W4384705463 hasPublicationYear "2023" @default.
- W4384705463 type Work @default.
- W4384705463 citedByCount "0" @default.
- W4384705463 crossrefType "proceedings-article" @default.
- W4384705463 hasAuthorship W4384705463A5018257269 @default.
- W4384705463 hasAuthorship W4384705463A5026593207 @default.
- W4384705463 hasAuthorship W4384705463A5031307529 @default.
- W4384705463 hasAuthorship W4384705463A5047885427 @default.
- W4384705463 hasAuthorship W4384705463A5049815529 @default.
- W4384705463 hasAuthorship W4384705463A5065069377 @default.
- W4384705463 hasAuthorship W4384705463A5066195314 @default.
- W4384705463 hasAuthorship W4384705463A5090060327 @default.
- W4384705463 hasConcept C111919701 @default.
- W4384705463 hasConcept C11210021 @default.
- W4384705463 hasConcept C11413529 @default.
- W4384705463 hasConcept C121332964 @default.
- W4384705463 hasConcept C124101348 @default.
- W4384705463 hasConcept C155281189 @default.
- W4384705463 hasConcept C158622935 @default.
- W4384705463 hasConcept C173608175 @default.
- W4384705463 hasConcept C17744445 @default.
- W4384705463 hasConcept C199539241 @default.
- W4384705463 hasConcept C202444582 @default.
- W4384705463 hasConcept C2776359362 @default.
- W4384705463 hasConcept C2779960059 @default.
- W4384705463 hasConcept C33923547 @default.
- W4384705463 hasConcept C41008148 @default.
- W4384705463 hasConcept C62520636 @default.
- W4384705463 hasConcept C68339613 @default.
- W4384705463 hasConcept C80444323 @default.
- W4384705463 hasConcept C89198739 @default.
- W4384705463 hasConcept C94625758 @default.
- W4384705463 hasConceptScore W4384705463C111919701 @default.
- W4384705463 hasConceptScore W4384705463C11210021 @default.
- W4384705463 hasConceptScore W4384705463C11413529 @default.
- W4384705463 hasConceptScore W4384705463C121332964 @default.
- W4384705463 hasConceptScore W4384705463C124101348 @default.
- W4384705463 hasConceptScore W4384705463C155281189 @default.
- W4384705463 hasConceptScore W4384705463C158622935 @default.
- W4384705463 hasConceptScore W4384705463C173608175 @default.
- W4384705463 hasConceptScore W4384705463C17744445 @default.
- W4384705463 hasConceptScore W4384705463C199539241 @default.
- W4384705463 hasConceptScore W4384705463C202444582 @default.
- W4384705463 hasConceptScore W4384705463C2776359362 @default.
- W4384705463 hasConceptScore W4384705463C2779960059 @default.
- W4384705463 hasConceptScore W4384705463C33923547 @default.
- W4384705463 hasConceptScore W4384705463C41008148 @default.
- W4384705463 hasConceptScore W4384705463C62520636 @default.
- W4384705463 hasConceptScore W4384705463C68339613 @default.
- W4384705463 hasConceptScore W4384705463C80444323 @default.
- W4384705463 hasConceptScore W4384705463C89198739 @default.
- W4384705463 hasConceptScore W4384705463C94625758 @default.