23 citations · 29 across the 10 of their papers we have counts for
5 papers · 1 filter
Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy
Md. Khaledur Rahman, Ariful Azad
Graph Neural Networks (GNNs) are widely used to perform different machine learning tasks on graphs. As the size of the graphs grows, and the GNNs get deeper, training and inference…
MarkovGNN: Graph Neural Networks on Markov Diffusion
Md. Khaledur Rahman, Abhigya Agrawal, Ariful Azad
Most real-world networks contain well-defined community structures where nodes are densely connected internally within communities. To learn from these networks, we develop MarkovG…
A Comprehensive Analytical Survey on Unsupervised and Semi-Supervised Graph Representation Learning Methods
Md. Khaledur Rahman, Ariful Azad
Graph representation learning is a fast-growing field where one of the main objectives is to generate meaningful representations of graphs in lower-dimensional spaces. The learned…
FusedMM: A Unified SDDMM-SpMM Kernel for Graph Embedding and Graph Neural Networks
Md. Khaledur Rahman, Majedul Haque Sujon, Ariful Azad
We develop a fused matrix multiplication kernel that unifies sampled dense-dense matrix multiplication and sparse-dense matrix multiplication under a single operation called FusedM…
Training Sensitivity in Graph Isomorphism Network
Md. Khaledur Rahman
Graph neural network (GNN) is a popular tool to learn the lower-dimensional representation of a graph. It facilitates the applicability of machine learning tasks on graphs by incor…