Výsledky vyhledávání - "Naganand Yadati"

A Convex Formulation for Graph Convolutional Training: Two Layer Case

Autor: Naganand Yadati

Publikováno v: 2022 IEEE International Conference on Data Mining (ICDM).

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9e32b06ef4e412b9a4141f0965d8c727
https://doi.org/10.1109/icdm54844.2022.00168

Zobrazit plný text záznamu

KVQA: Knowledge-Aware Visual Question Answering

Autor: Naganand Yadati, Sanket Shah, Anand Mishra, Partha Pratim Talukdar

Publikováno v: AAAI
Scopus-Elsevier

Visual Question Answering (VQA) has emerged as an important problem spanning Computer Vision, Natural Language Processing and Artificial Intelligence (AI). In conventional VQA, one may ask questions about an image which can be answered purely based o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9d139721312e0886013e5d125e61590c
https://doi.org/10.1609/aaai.v33i01.33018876

Zobrazit plný text záznamu

Knowledge Base Question Answering through Recursive Hypergraphs

Autor: Srinidhi G, Dayanidhi R S, Vaishnavi S, Naganand Yadati, Indira K M

Publikováno v: EACL

Knowledge Base Question Answering (KBQA) is the problem of predicting an answer for a factoid question over a given knowledge base (KB). Answering questions typically requires reasoning over multiple links in the given KB. Humans tend to answer quest

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b739347de807b8661f50b64ac909a81f
https://doi.org/10.18653/v1/2021.eacl-main.35

Zobrazit plný text záznamu

Graph Neural Networks for Soft Semi-Supervised Learning on Hypergraphs

Autor: Shahab Asoodeh, Anand Louis, Tingran Gao, Partha Pratim Talukdar, Naganand Yadati

Publikováno v: Advances in Knowledge Discovery and Data Mining ISBN: 9783030757618
PAKDD (1)

Graph-based semi-supervised learning (SSL) assigns labels to initially unlabelled vertices in a graph. Graph neural networks (GNNs), esp. graph convolutional networks (GCNs), are at the core of the current-state-of-the art models for graph-based SSL

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1a7dd93013d79613562140f61dbaed73
https://doi.org/10.1007/978-3-030-75762-5_36

Zobrazit plný text záznamu

NHP: Neural Hypergraph Link Prediction

Autor: Madhav Nimishakavi, Partha Pratim Talukdar, Vikram Nitin, Naganand Yadati, Anand Louis, Prateek Yadav

Publikováno v: CIKM

Link prediction insimple graphs is a fundamental problem in which new links between vertices are predicted based on the observed structure of the graph. However, in many real-world applications, there is a need to model relationships among vertices t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::360dedc0c9cded069b99583fde60a47d
https://doi.org/10.1145/3340531.3411870

Zobrazit plný text záznamu

Graph-based Deep Learning in Natural Language Processing

Autor: Naganand Yadati, Shikhar Vashishth, Partha Pratim Talukdar

Publikováno v: COMAD/CODS

This tutorial aims to introduce recent advances in graph-based deep learning techniques such as Graph Convolutional Networks (GCNs) for Natural Language Processing (NLP). It provides a brief introduction to deep learning methods on non-Euclidean doma

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f41910e440e8f9c93d942581bacde405
https://doi.org/10.1145/3371158.3371232

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání