Search Results for author: Ramanarayan Mohanty

Found 9 papers, 2 papers with code

DistGNN-MB: Distributed Large-Scale Graph Neural Network Training on x86 via Minibatch Sampling

no code implementations11 Nov 2022 Md Vasimuddin, Ramanarayan Mohanty, Sanchit Misra, Sasikanth Avancha

DistGNN-MB trains GraphSAGE and GAT 10x and 17. 2x faster, respectively, as compute nodes scale from 2 to 32.

DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks

no code implementations14 Apr 2021 Vasimuddin Md, Sanchit Misra, Guixiang Ma, Ramanarayan Mohanty, Evangelos Georganas, Alexander Heinecke, Dhiraj Kalamkar, Nesreen K. Ahmed, Sasikanth Avancha

Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible.

graph partitioning

Deep Graph Library Optimizations for Intel(R) x86 Architecture

1 code implementation13 Jul 2020 Sasikanth Avancha, Vasimuddin Md, Sanchit Misra, Ramanarayan Mohanty

The Deep Graph Library (DGL) was designed as a tool to enable structure learning from graphs, by supporting a core abstraction for graphs, including the popular Graph Neural Networks (GNN).

A Semi-supervised Spatial Spectral Regularized Manifold Local Scaling Cut With HGF for Dimensionality Reduction of Hyperspectral Images

no code implementations20 Nov 2018 Ramanarayan Mohanty, SL Happy, Aurobinda Routray

The underlying idea of the proposed method is to exploit the limited labeled information from both the spectral and spatial domains along with the abundant unlabeled samples to facilitate the classification task by retaining the original distribution of the data.

Dimensionality Reduction General Classification

A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image

no code implementations22 Jul 2018 Ramanarayan Mohanty, S. L. Happy, Nilesh Suthar, Aurobinda Routray

The underlying idea of this method is to generate the optimal projection matrix by considering both the sparsity as well as the correlation of the data samples.

Dimensionality Reduction

A Supervised Geometry-Aware Mapping Approach for Classification of Hyperspectral Images

no code implementations7 Jul 2018 Ramanarayan Mohanty, S. L. Happy, Aurobinda Routray

The underlying idea of this method is to obtain a linear projection matrix by solving a nonlinear objective function based on the intrinsic geometrical structure of the data.

Classification Classification Of Hyperspectral Images +2

Graph Scaling Cut with L1-Norm for Classification of Hyperspectral Images

no code implementations9 Sep 2017 Ramanarayan Mohanty, S. L. Happy, Aurobinda Routray

The underlying idea of this method is to generate the optimal projection matrix by retaining the original distribution of the data.

Classification Of Hyperspectral Images Dimensionality Reduction +1

Cannot find the paper you are looking for? You can Submit a new open access paper.