Communication-efficient algorithms for parallel latent Dirichlet allocation
| LEADER | caa a22 4500 | ||
|---|---|---|---|
| 001 | 60546846X | ||
| 003 | CHVBK | ||
| 005 | 20210128100316.0 | ||
| 007 | cr unu---uuuuu | ||
| 008 | 210128e20150101xx s 000 0 eng | ||
| 024 | 7 | 0 | |a 10.1007/s00500-014-1376-8 |2 doi |
| 035 | |a (NATIONALLICENCE)springer-10.1007/s00500-014-1376-8 | ||
| 245 | 0 | 0 | |a Communication-efficient algorithms for parallel latent Dirichlet allocation |h [Elektronische Daten] |c [Jian-Feng Yan, Jia Zeng, Yang Gao, Zhi-Qiang Liu] |
| 520 | 3 | |a Latent Dirichlet allocation (LDA) is a popular topic modeling method which has found many multimedia applications, such as motion analysis and image categorization. Communication cost is one of the main bottlenecks for large-scale parallel learning of LDA. To reduce communication cost, we introduce Zipf's law and propose novel parallel LDA algorithms that communicate only partial important information at each learning iteration. The proposed algorithms are much more efficient than the current state-of-the-art algorithms in both communication and computation costs. Extensive experiments on large-scale data sets demonstrate that our algorithms can greatly reduce communication and computation costs to achieve a better scalability. | |
| 540 | |a Springer-Verlag Berlin Heidelberg, 2014 | ||
| 690 | 7 | |a Latent Dirichlet allocation |2 nationallicence | |
| 690 | 7 | |a Parallel learning |2 nationallicence | |
| 690 | 7 | |a Zipf's law |2 nationallicence | |
| 690 | 7 | |a Belief propagation |2 nationallicence | |
| 690 | 7 | |a Gibbs sampling |2 nationallicence | |
| 700 | 1 | |a Yan |D Jian-Feng |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | |
| 700 | 1 | |a Zeng |D Jia |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | |
| 700 | 1 | |a Gao |D Yang |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | |
| 700 | 1 | |a Liu |D Zhi-Qiang |u School of Creative Media, City University of Hong Kong, Hong Kong, China |4 aut | |
| 773 | 0 | |t Soft Computing |d Springer Berlin Heidelberg |g 19/1(2015-01-01), 3-11 |x 1432-7643 |q 19:1<3 |1 2015 |2 19 |o 500 | |
| 856 | 4 | 0 | |u https://doi.org/10.1007/s00500-014-1376-8 |q text/html |z Onlinezugriff via DOI |
| 898 | |a BK010053 |b XK010053 |c XK010000 | ||
| 900 | 7 | |a Metadata rights reserved |b Springer special CC-BY-NC licence |2 nationallicence | |
| 908 | |D 1 |a research-article |2 jats | ||
| 949 | |B NATIONALLICENCE |F NATIONALLICENCE |b NL-springer | ||
| 950 | |B NATIONALLICENCE |P 856 |E 40 |u https://doi.org/10.1007/s00500-014-1376-8 |q text/html |z Onlinezugriff via DOI | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Yan |D Jian-Feng |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Zeng |D Jia |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Gao |D Yang |u School of Computer Science and Technology, Soochow University, 215006, Suzhou, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 700 |E 1- |a Liu |D Zhi-Qiang |u School of Creative Media, City University of Hong Kong, Hong Kong, China |4 aut | ||
| 950 | |B NATIONALLICENCE |P 773 |E 0- |t Soft Computing |d Springer Berlin Heidelberg |g 19/1(2015-01-01), 3-11 |x 1432-7643 |q 19:1<3 |1 2015 |2 19 |o 500 | ||