Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Yadati, Naganand"'
Autor:
Sanyal, Soumya, Balachandran, Janakiraman, Yadati, Naganand, Kumar, Abhishek, Rajagopalan, Padmini, Sanyal, Suchismita, Talukdar, Partha
Developing accurate, transferable and computationally inexpensive machine learning models can rapidly accelerate the discovery and development of new materials. Some of the major challenges involved in developing such models are, (i) limited availabi
Externí odkaz:
http://arxiv.org/abs/1811.05660
Autor:
Yadati, Naganand, Nimishakavi, Madhav, Yadav, Prateek, Nitin, Vikram, Louis, Anand, Talukdar, Partha
In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex relationships. The obv
Externí odkaz:
http://arxiv.org/abs/1809.02589
Autor:
Yadav, Prateek, Nimishakavi, Madhav, Yadati, Naganand, Vashishth, Shikhar, Rajkumar, Arun, Talukdar, Partha
Semi-supervised learning on graph structured data has received significant attention with the recent introduction of Graph Convolution Networks (GCN). While traditional methods have focused on optimizing a loss augmented with Laplacian regularization
Externí odkaz:
http://arxiv.org/abs/1805.11365
Publikováno v:
ACM International Conference Proceeding Series; 1/5/2020, p371-372, 2p
