Naganand Yadati

Education

• 2016 - 2021: Ph.D. from the Indian Institute of Science with thesis titled Deep Learning over Hypergraphs advised by Prof. Partha Talukdar.
• 2014 - 2016: M. Tech. from IIIT Bangalore with thesis advised by Prof. Ashish Choudhury.

Research Focus

• Deep Learning with emphasis on Graph Neural Networks
• Learning on Rich Structures (e.g., Hypergraphs, Causal Graphs)

Selected Publications, Tutorial from Google Scholar

• Graph Neural Networks for Soft Semi-Supervised Learning on Hypergraphs [code]
  Naganand Yadati, Tingran Gao, Shahab Asoodeh, Partha Talukdar, and Anand Louis
  PAKDD 2021

• Knowledge Base Question Answering through Recursive Hypergraphs [slides]
  Naganand Yadati, Dayanidhi R S, Vaishnavi S, Indira K M, and Srinidhi G
  EACL 2021

• Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs [code, slides]
  Naganand Yadati
  NeurIPS 2020

• NHP: Neural Hypergraph Link Prediction [code, slides]
  Naganand Yadati, Vikram Nitin, Madhav Nimishakavi, Prateek Yadav, Anand Louis, and Partha Talukdar
  CIKM 2020

• HyperGCN: A New Method for Training Graph Convolutional Networks on Hypergraphs [code, slides]
  Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, and Partha Talukdar
  NeurIPS 2019

• Tutorial on Graph-based Deep Learning in Natural Language Processing [video, slides]
  Shikhar Vashishth, Naganand Yadati, and Partha Talukdar
  EMNLP-IJCNLP 2019, CoDS-COMAD 2020