Anand Sivasubramaniam — accepted AI-conference papers

2022

Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks

Morteza Ramezani, Weilin Cong, Mehrdad Mahdavi, Mahmut Kandemir, Anand Sivasubramaniam

ICLR 2022poster

Despite the recent success of Graph Neural Networks (GNNs), training GNNs on large graphs remains challenging. The limited resource capacities of the existing servers, the dependency between nodes in a graph, and the privacy concern due to the centralized storage and model learning have spurred the…

Cited by 44 Source ↗PDF ↗Scholar ↗

2020

GCN meets GPU: Decoupling “When to Sample” from “How to Sample”

Morteza Ramezani, Weilin Cong, Mehrdad Mahdavi, Anand Sivasubramaniam, Mahmut Kandemir

NeurIPS 2020poster

Sampling-based methods promise scalability improvements when paired with stochastic gradient descent in training Graph Convolutional Networks (GCNs). While effective in alleviating the neighborhood explosion, due to bandwidth and memory bottlenecks, these methods lead to computational overheads in p…

Cited by 41 Source ↗PDF ↗Scholar ↗