Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ariful Azad

Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed

Apr 25, 2021
Nicholas Majeske, Bidisha Abesh, Chen Zhu, Ariful Azad

* 5 pages, 3 figures 

  Access Paper or Ask Questions

Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data

Apr 07, 2021
Tingyi Wanyan, Jing Zhang, Ying Ding, Ariful Azad, Zhangyang Wang, Benjamin S Glicksberg

  Access Paper or Ask Questions

Deep Learning with Heterogeneous Graph Embeddings for Mortality Prediction from Electronic Health Records

Dec 28, 2020
Tingyi Wanyan, Hossein Honarvar, Ariful Azad, Ying Ding, Benjamin S. Glicksberg

  Access Paper or Ask Questions

FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks

Nov 07, 2020
Md. Khaledur Rahman, Majedul Haque Sujon, Ariful Azad

* 11 pages, Under review in IPDPS 2021 

  Access Paper or Ask Questions

Force2Vec: Parallel force-directed graph embedding

Sep 17, 2020
Md. Khaledur Rahman, Majedul Haque Sujon, Ariful Azad

* Accepted for publication in ICDM 2020 as a regular paper 

  Access Paper or Ask Questions

Attribute2vec: Deep Network Embedding Through Multi-Filtering GCN

Apr 03, 2020
Tingyi Wanyan, Chenwei Zhang, Ariful Azad, Xiaomin Liang, Daifeng Li, Ying Ding

  Access Paper or Ask Questions

Integrated Model, Batch and Domain Parallelism in Training Neural Networks

May 16, 2018
Amir Gholami, Ariful Azad, Peter Jin, Kurt Keutzer, Aydin Buluc

* 30th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), 2018 
* 11 pages 

  Access Paper or Ask Questions

Communication-Avoiding Optimization Methods for Distributed Massive-Scale Sparse Inverse Covariance Estimation

Apr 08, 2018
Penporn Koanantakool, Alnur Ali, Ariful Azad, Aydin Buluc, Dmitriy Morozov, Leonid Oliker, Katherine Yelick, Sang-Yun Oh

* Main paper: 15 pages, appendix: 24 pages 

  Access Paper or Ask Questions