Kashob Kumar Roy

Kashob Kumar Roy, Amit Roy, AKM Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali

Node embedding using mutual information and self-supervision based bi-level aggregation

2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2021

• graph neural networks
• Mutual information
• node embeddings
• self-supervised learning
• long-range dependencies
• node clustering

Amit Roy, Kashob Kumar Roy, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman

Unified spatio-temporal modeling for traffic forecasting using graph neural network

2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2021

• spectral graph convolution
• traffic prediction
• graph neural networks
• spatio-temporal graph convolutional network
• spatio-temporal graph
• PeMS dataset

• SDG 11Sustainable Cities and Communities

Kashob Kumar Roy, Amit Roy, AKM Mahbubur Rahman, M Ashraful Amin, Amin Ahsan Ali

Structure-aware hierarchical graph pooling using information bottleneck

2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, 2021

• graph pooling
• information bottleneck
• adversarial robustness
• graph neural networks
• graph classification

Amit Roy, Kashob Kumar Roy, Amin Ahsan Ali, M Ashraful Amin, AKM Mahbubur Rahman

SST-GNN: simplified spatio-temporal traffic forecasting model using graph neural network

Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 90–102, 2021

• graph neural networks
• positional encoding
• traffic prediction
• temporal dependencies
• periodic traffic patterns
• PEMS
• long-range dependencies
• street intersections
• spatial dependence

• SDG 11Sustainable Cities and Communities