TY - GEN
T1 - ElDA
T2 - 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2020
AU - Wang, Shilong
AU - Li, Da
AU - Yu, Hengyong
AU - Liu, Hang
N1 - Publisher Copyright:
© 2020 Copyright held by the owner/author(s).
PY - 2020/2/19
Y1 - 2020/2/19
N2 - Latent Dirichlet Allocation (LDA) is a statistical approach for topic modeling with a wide range of applications. In spite of the significance, we observe very few attempts from system track to improve LDA, let alone the algorithm and system codesigned efforts. To this end, we propose eLDA with an algorithm-system codesigned optimization. Particularly, we introduce a novel three-branch sampling mechanism to taking advantage of the convergence heterogeneity of various tokens in order to reduce redundant sampling task. Our evaluation shows that eLDA outperforms the state-of-the-arts.
AB - Latent Dirichlet Allocation (LDA) is a statistical approach for topic modeling with a wide range of applications. In spite of the significance, we observe very few attempts from system track to improve LDA, let alone the algorithm and system codesigned efforts. To this end, we propose eLDA with an algorithm-system codesigned optimization. Particularly, we introduce a novel three-branch sampling mechanism to taking advantage of the convergence heterogeneity of various tokens in order to reduce redundant sampling task. Our evaluation shows that eLDA outperforms the state-of-the-arts.
UR - http://www.scopus.com/inward/record.url?scp=85082391040&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082391040&partnerID=8YFLogxK
U2 - 10.1145/3332466.3374517
DO - 10.1145/3332466.3374517
M3 - Conference contribution
AN - SCOPUS:85082391040
T3 - Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP
SP - 407
EP - 408
BT - PPoPP 2020 - Proceedings of the 2020 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
PB - Association for Computing Machinery
Y2 - 22 February 2020 through 26 February 2020
ER -