S
Svetha Venkatesh
Researcher at Deakin University
Publications - 864
Citations - 20118
Svetha Venkatesh is an academic researcher from Deakin University. The author has contributed to research in topics: Bayesian optimization & Computer science. The author has an hindex of 60, co-authored 828 publications receiving 16441 citations. Previous affiliations of Svetha Venkatesh include Australian National University & National University of Singapore.
Papers
More filters
Posted ContentDOI
Prediction of drug–target binding affinity using graph neural networks
TL;DR: GraphDTA as mentioned in this paper uses graph convolutional networks to learn drug-target binding affinity, which can not only predict the affinity better than non-deep learning models, but also outperform competing deep learning approaches.
Journal ArticleDOI
Estimation of the prevalence of adverse drug reactions from social media
TL;DR: Advances in lightning-fast cluster computing was employed to process large scale data, consisting of 6.4 terabytes of data containing 3.8 billion records from all the media, demonstrating the capability of advanced techniques in machine learning to aid in the discovery of meaningful patterns from medical data, and social media data, at scale.
Proceedings Article
Self-Attentive Associative Memory
TL;DR: This paper proposes to separate the storage of individual experiences (item memory) and their occurring relationships (relational memory) through a novel Self-attentive Associative Memory (SAM) operator, and achieves competitive results with the proposed two-memory model.
Proceedings ArticleDOI
Dynamic Privacy in a Smart House Environment
TL;DR: A dynamic method for altering the level of privacy in the environment based on the context, the situation within the environment, encompassing factors relevant to ensuring the occupant's safety and privacy is proposed.
Posted ContentDOI
Predicting drug–target binding affinity with graph neural networks
TL;DR: GraphDTA as discussed by the authors uses graph neural networks to predict drug-target affinity, which is a generic solution for any collaborating filtering or recommendation problem where either data input can be represented as a graph.