no code implementations • 19 Jan 2024 • Pratyush Dhingra, Chukwufumnanya Ogbogu, Biresh Kumar Joardar, Janardhan Rao Doppa, Ananth Kalyanaraman, Partha Pratim Pande
Experimental results demonstrate that FARe framework can restore GNN test accuracy by 47. 6% on faulty ReRAM hardware with a ~1% timing overhead compared to the fault-free counterpart.
1 code implementation • 3 Nov 2023 • Krishu K. Thapa, Bhupinderjeet Singh, Supriya Savalkar, Alan Fern, Kirti Rajagopalan, Ananth Kalyanaraman
Our hypothesis is that attention has a unique ability to capture and exploit correlations that may exist across locations or the temporal spectrum (or both).
1 code implementation • 29 Dec 2017 • Ananth Kalyanaraman, Methun Kamruzzaman, Bala Krishnamoorthy
For the special case when G is a directed acyclic graph (DAG), we show that Max-IP can be solved in polynomial time - in O(mnd_i) where d_i is the maximum indegree of a vertex in G. In the more general problem IP, the goal is to find a collection of edge-disjoint interesting paths such that the overall sum of their interestingness scores is maximized.
Computational Geometry Data Structures and Algorithms Algebraic Topology 05C85, 68Q25, 62H30, 55U99 G.2.2; F.2.2
1 code implementation • 14 Jul 2017 • Methun Kamruzzaman, Ananth Kalyanaraman, Bala Krishnamoorthy, Stefan Hey, Patrick Schnable
Notably, our approach shows how environmental factors could influence phenotypic behavior, and how that effect varies across different genotypes and different time scales.