34 citations · 104 across the 11 of their papers we have counts for
14 papers
Rightsizing Clusters for Time-Limited Tasks
Venkatesan T. Chakaravarthy, Padmanabha V. Seshadri, Pooja Aggarwal +4
In conventional public clouds, designing a suitable initial cluster for a given application workload is important in reducing the computational foot-print during run-time. In edge…
GREED: A Neural Framework for Learning Graph Distance Functions
Rishabh Ranjan, Siddharth Grover, Sourav Medya +3
Among various distance functions for graphs, graph and subgraph edit distances (GED and SED respectively) are two of the most popular and expressive measures. Unfortunately, exact…
Efficient Scaling of Dynamic Graph Neural Networks
Venkatesan T. Chakaravarthy, Shivmaran S. Pandian, Saurabh Raje +3
We present distributed algorithms for training dynamic Graph Neural Networks (GNN) on large scale graphs spanning multi-node, multi-GPU systems. To the best of our knowledge, this…
PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
Saurabh Goyal, Anamitra R. Choudhury, Saurabh M. Raje +3
We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pert…
On Optimizing Distributed Tucker Decomposition for Sparse Tensors
Venkatesan T. Chakaravarthy, Jee W. Choi, Douglas J. Joseph +4
The Tucker decomposition generalizes the notion of Singular Value Decomposition (SVD) to tensors, the higher dimensional analogues of matrices. We study the problem of constructing…
On Optimizing Distributed Tucker Decomposition for Dense Tensors
Venkatesan T Chakaravarthy, Jee W Choi, Douglas J Joseph +4
The Tucker decomposition expresses a given tensor as the product of a small core tensor and a set of factor matrices. Apart from providing data compression, the construction is use…