Publication
CIKM 2016
Conference paper

Distributed deep learning for question answering

View publication

Abstract

This paper is an empirical study of the distributed deep learning for question answering subtasks: answer selection and question classification. Comparison studies of SGD, MSGD, ADADELTA, ADAGRAD, ADAM/ADAMAX, RM-SPROP, DOWNPOUR and EASGD/EAMSGD algorithms have been presented. Experimental results show that the distributed framework based on the message passing interface can accelerate the convergence speed at a sublinear scale. This paper demonstrates the importance of distributed training. For example, with 48 workers, a 24 × speedup is achievable for the answer selection task and running time is decreased from 138.2 hours to 5.81 hours, which will increase the productivity significantly.

Date

Publication

CIKM 2016

Authors

Share