3 papers
cs.DC2026
Communication-Efficient, 2D Parallel Stochastic Gradient Descent for Distributed-Memory Optimization
Aditya Devarakonda, Ramakrishnan Kannan
Distributed-memory implementations of numerical optimization algorithm, such as stochastic gradient descent (SGD), require interprocessor communication at every iteration of the al…
cs.SI2025
Community detection robustness of graph neural networks
Jaidev Goel, Pablo Moriano, Ramakrishnan Kannan +1
Graph neural networks (GNNs) are increasingly widely used for community detection in attributed networks. They combine structural topology with node attributes through message pass…
physics.soc-ph2025
Robustness of graph embedding methods for community detection
Zhi-Feng Wei, Pablo Moriano, Ramakrishnan Kannan
This study investigates the robustness of graph embedding methods for community detection in the face of network perturbations, specifically edge deletions. Graph embedding techniq…