Search Results for author: Naganand Yadati

Found 10 papers, 4 papers with code

Neural Message Passing for Multi-Relational Ordered and Recursive Hypergraphs

no code implementations NeurIPS 2020 Naganand Yadati

Message passing neural network (MPNN) has recently emerged as a successful framework by achieving state-of-the-art performances on many graph-based learning tasks.

HyperGCN: A New Method For Training Graph Convolutional Networks on Hypergraphs

1 code implementation NeurIPS 2019 Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, Partha Talukdar

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise.

Biologically Plausible Neural Networks via Evolutionary Dynamics and Dopaminergic Plasticity

no code implementations NeurIPS Workshop Neuro_AI 2019 Sruthi Gorantla, Anand Louis, Christos H. Papadimitriou, Santosh Vempala, Naganand Yadati

Artificial neural networks (ANNs) lack in biological plausibility, chiefly because backpropagation requires a variant of plasticity (precise changes of the synaptic weights informed by neural events that occur downstream in the neural circuit) that is profoundly incompatible with the current understanding of the animal brain.

KVQA: Knowledge-Aware Visual Question Answering

no code implementations AAAI Conference on Artificial Intelligence 2019 Sanket Shah, Hyderabad Anand Mishra, Naganand Yadati, Partha Pratim Talukdar

In spite of this progress, the important problem of answering questions requiring world knowledge about named entities (e. g., Barack Obama, White House, United Nations) in the image has not been addressed in prior research.

Knowledge Graphs Question Answering +2

MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction

1 code implementation14 Nov 2018 Soumya Sanyal, Janakiraman Balachandran, Naganand Yadati, Abhishek Kumar, Padmini Rajagopalan, Suchismita Sanyal, Partha Talukdar

Some of the major challenges involved in developing such models are, (i) limited availability of materials data as compared to other fields, (ii) lack of universal descriptor of materials to predict its various properties.

Band Gap Formation Energy +1

HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

1 code implementation7 Sep 2018 Naganand Yadati, Madhav Nimishakavi, Prateek Yadav, Vikram Nitin, Anand Louis, Partha Talukdar

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise.

Lovasz Convolutional Networks

1 code implementation29 May 2018 Prateek Yadav, Madhav Nimishakavi, Naganand Yadati, Shikhar Vashishth, Arun Rajkumar, Partha Talukdar

We analyse local and global properties of graphs and demonstrate settings where LCNs tend to work better than GCNs.

Multi-class Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.