no code implementations • 21 Nov 2023 • Sai Munikoti, Anurag Acharya, Sridevi Wagle, Sameera Horawalavithana
We train a graph neural network on the curated document graph to act as a structural encoder for the corresponding passages retrieved during the model pretraining.
1 code implementation • 15 Nov 2023 • Sridevi Wagle, Sai Munikoti, Anurag Acharya, Sara Smith, Sameera Horawalavithana
This research investigates how uncertainty scores vary when scientific knowledge is incorporated as pretraining and retrieval data and explores the relationship between uncertainty scores and the accuracy of model-generated outputs.
no code implementations • 7 Nov 2023 • Sai Munikoti, Anurag Acharya, Sridevi Wagle, Sameera Horawalavithana
Despite the dramatic progress in Large Language Model (LLM) development, LLMs often provide seemingly plausible but not factual information, often referred to as hallucinations.
1 code implementation • 17 Oct 2023 • Anurag Acharya, Sai Munikoti, Aaron Hellinger, Sara Smith, Sridevi Wagle, Sameera Horawalavithana
As LLMs have become increasingly popular, they have been used in almost every field.
1 code implementation • 3 Jul 2023 • Sameera Horawalavithana, Sai Munikoti, Ian Stewart, Henry Kvinge
Instruction finetuning is a popular paradigm to align large language models (LLM) with human intent.
no code implementations • 1 Jun 2023 • Shweta Dahale, Sai Munikoti, Balasubramaniam Natarajan
Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially for the time series imputation with irregularly sampled measurements.
no code implementations • 31 May 2023 • Laya Das, Sai Munikoti, Mahantesh Halappanavar
We hypothesize that leveraging multiple graphs of the same type/class can improve the quality of learnt representations in the model by extracting features that are universal to the class of graphs.
no code implementations • 7 Nov 2022 • Shweta Dahale, Sai Munikoti, Balasubramaniam Natarajan, Rui Yang
Under a smart grid paradigm, there has been an increase in sensor installations to enhance situational awareness.
no code implementations • 16 Jun 2022 • Sai Munikoti, Deepesh Agarwal, Laya Das, Mahantesh Halappanavar, Balasubramaniam Natarajan
Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields, including pattern recognition, robotics, recommendation-systems, and gaming.
no code implementations • 30 May 2022 • Sai Munikoti, Balasubramaniam Natarajan, Mahantesh Halappanavar
However, there are serious limitations in current approaches such as: (1) IM formulations only consider influence via spread and ignore self activation; (2) scalability to large graphs; (3) generalizability across graph families; (4) low computational efficiency with a large running time to identify seed sets for every test network.
no code implementations • 20 May 2022 • Sai Munikoti, Deepesh Agarwal, Laya Das, Balasubramaniam Natarajan
Graph Neural Networks (GNN) provide a powerful framework that elegantly integrates Graph theory with Machine learning for modeling and analysis of networked data.
no code implementations • 3 Jun 2021 • Sai Munikoti, Mohammad Abujubbeh, Kumarsinh Jhala, Balasubramaniam Natarajan
VIS is derived analytically in a computationally efficient manner and its efficacy to identify DVI nodes is validated using the IEEE 37-node test system.
no code implementations • 26 Dec 2020 • Sai Munikoti, Laya Das, Balasubramaniam Natarajan
Most existing methods of critical node identification are based on an iterative approach that explores each node/link of a graph.
no code implementations • 26 Dec 2020 • Sai Munikoti, Laya Das, Balasubramaniam Natarajan
To overcome these challenges, this article proposes a scalable and generic graph neural network (GNN) based framework for identifying critical nodes/links in large complex networks.