Research
I'm interested in applying Machine Learning to Scale Up Combinatorial Algorithms. Some of the Application domains are Graph Analytics, Genomics, and Life Sciences. My research requires usage of Structured Prediction, Imitation Learning, Deep Learning, Reinforcecment Learning. I have also worked on using Attention based models in Deep Neural Network to improve Text-Dependent Speaker Verification.
|
Publications
Select-and-Evaluate: Learning for Large-Scale Knowledge Graph Search
F A Rezaur Rahman Chowdhury*,
Chao Ma*, Md Rakibul Islam, Mohammad Hossein Namaki, Mohammad Omar Faruk ,
Janardhan Rao Doppa
(* denotes equal contribution)
Journal of Machine Learning Research , Proceedings Track, Vol 77, PP 129-144, 2017.
We developed a learning framework to answer graph pattern queries in large scale knowledge graph called Select-and-Evaluate (SCALE) using Imitation Learning approach.
|
Learning to Speed Up Query Planning in Graph Databases
Mohammad Hossein Namaki*,
F A Rezaur Rahman Chowdhury*,
Md Rakibul Islam,
Janardhan Rao Doppa,
Yinghui Wu
(* denotes equal contribution)
Proceedings of 27th International Conference on Automated Planning and Scheduling (ICAPS), 2017
.We present a Learning to Plan (L2P) framework that is applicable to a large class of query reasoners that follow the Threshold Algorithm (TA) approach.
|
Attention-based models for Text-dependent speaker verification
F A Rezaur Rahman Chowdhury,
Quan Wang, Ignacio Lopez Moreno, Li Wan
To appear in Proceedings of 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018
We use Attention based Deep Neural Network models to improve Text-Dependent Speaker Verification.
|
Randomized Greedy Search for Structured Prediction: Amortized Inference and Learning
Chao Ma*,
F A Rezaur Rahman Chowdhury*,
Aryan Deshwal, Md Rakibul Islam, Janardhan Rao Doppa, Dan Roth
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2019
|
Learning to Fold RNAs in Linear Time
F A Rezaur Rahman Chowdhury*,
He Zhang*,
Liang Huang
(* denotes equal contribution)
Submission Under Review in International Conference on Research in Computational Molecular Biology (RECOMB), 2020
We present a linear-time machine learning-based folding system, using recently proposed approximate folding tool LinearFold as inference engine, and structured SVM (sSVM) as training algorithm. Our tool is faster and more accurate than existing tools.
|
Talks and Abstracts
- At ACML 2017, I gave a talk on our work on Select-and-Evaluate Framework for Large-Scale Knowledge Graph Search
- At ISMB/ISCB 2019 RNA COSI track, Our work was presented as a poster of an accepted Abstract.
|
|