Scalable deep text comprehension for Cancer surveillance on high-performance computing
- ORNL
- University of Memphis
- LSUHSC-Louisiana Tumor Registry
- National Cancer Institute, Bethesda, MD
Background: Deep Learning (DL) has advanced the state-of-the-art capabilities in bioinformatics applications which has resulted in trends of increasingly sophisticated and computationally demanding models trained by larger and larger data sets. This vastly increased computational demand challenges the feasibility of conducting cutting-edge research. One solution is to distribute the vast computational workload across multiple computing cluster nodes with data parallelism algorithms. In this study, we used a High-Performance Computing environment and implemented the Downpour Stochastic Gradient Descent algorithm for data parallelism to train a Convolutional Neural Network (CNN) for the natural language processing task of information extraction from a massive dataset of cancer pathology reports. We evaluated the scalability improvements using data parallelism training and the Titan supercomputer at Oak Ridge Leadership Computing Facility. To evaluate scalability, we used different numbers of worker nodes and performed a set of experiments comparing the effects of different training batch sizes and optimizer functions.Results: We found that Adadelta would consistently converge at a lower validation loss, though requiring over twice as many training epochs as the fastest converging optimizer, RMSProp. The Adam optimizer consistently achieved a close 2nd place minimum validation loss significantly faster; using a batch size of 16 and 32 allowed the network to converge in only 4.5 training epochs.Conclusions: We demonstrated that the networked training process is scalable across multiple compute nodes communicating with message passing interface while achieving higher classification accuracy compared to a traditional machine learning algorithm.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1491345
- Resource Relation:
- Journal Volume: 19; Journal Issue: S18; Conference: SuperComputing 17 - Denver, Colorado, United States of America - 11/12/2017 5:00:00 AM-11/17/2017 5:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
The Case for Strong Scaling in Deep Learning: Training Large 3D CNNs with Hybrid Parallelism
FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters