N
Naganand Yadati
Researcher at Indian Institute of Science
Publications - 16
Citations - 444
Naganand Yadati is an academic researcher from Indian Institute of Science. The author has contributed to research in topics: Graph (abstract data type) & Hypergraph. The author has an hindex of 7, co-authored 15 publications receiving 219 citations.
Papers
More filters
Posted Content
HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs
Naganand Yadati,Madhav Nimishakavi,Prateek Yadav,Vikram Nitin,Anand Louis,Partha Pratim Talukdar +5 more
TL;DR: HyperGCN as mentioned in this paper is a graph convolutional network (GCN) for hypergraph-based semi-supervised learning (SSL) where the goal is to assign labels to initially unlabeled vertices in a hypergraph.
Proceedings Article
HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs
Naganand Yadati,Madhav Nimishakavi,Prateek Yadav,Vikram Nitin,Anand Louis,Partha Pratim Talukdar +5 more
TL;DR: This work proposes HyperGCN, a novel GCN for SSL on attributed hypergraphs, and shows how it can be used as a learning-based approach for combinatorial optimisation on NP-hard hypergraph problems.
Journal ArticleDOI
KVQA: Knowledge-Aware Visual Question Answering
TL;DR: KVQA is introduced – the first dataset for the task of (world) knowledge-aware VQA and is the largest dataset for exploring V QA over large Knowledge Graphs (KG), which consists of 183K question-answer pairs involving more than 18K named entities and 24K images.
Posted Content
MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction.
Soumya Sanyal,Janakiraman Balachandran,Naganand Yadati,Abhishek Kumar,Padmini Rajagopalan,Suchismita Sanyal,Partha Pratim Talukdar +6 more
TL;DR: A new model (MT-CGCNN) is developed by integrating CGCNN with transfer learning based on multi-task (MT) learning that is able to reduce the test error when employed on correlated properties by upto 8%.
Proceedings ArticleDOI
NHP: Neural Hypergraph Link Prediction
Naganand Yadati,Vikram Nitin,Madhav Nimishakavi,Prateek Yadav,Anand Louis,Partha Pratim Talukdar +5 more
TL;DR: This paper proposes Neural Hyperlink Predictor (NHP), a deep learning-based approach for link prediction over directed hypergraphs that adapts Graph Convolutional Network (GCN) and proposes two variants of NHP --NHP-U and NHP-D -- for link Prediction over undirected and directedhypergraphs, respectively.