Bidisha Samanta is currently a researcher at Google India Research Lab. Prior to joining Google she completed her Ph.D from the department of Computer Science and Engineering, Indian Institute of Technology Kharagpur, India under the guidance of Prof. Niloy Ganguly. Her research interest lies in the area of deep generative models for non-euclidean data such as graph and text. During her Ph.D she was the recipient of the prestigious Google India Ph.D fellowship. Over the years she has published in top international conferences and peer reviewed journals such as AAAI, IJCAI, ACL, EMNLP, JMLR.
A deep generative model for molecular graphs
Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used to generate new, plausible data. However, current generative models are unable to work with molecular graphs due to their unique characteristics—their underlying structure is not Euclidean or grid-like, they remain isomorphic under permutation of the nodes labels, and they come with a different number of nodes and edges. In our work we propose a variational autoencoder for molecular graphs, whose encoder and decoder are specially designed to account for the above properties by means of several technical innovations. We further develop a gradient-based algorithm to optimize the decoder of our model so that it learns to generate molecules that maximize the value of a certain property of interest and, given a molecule of interest, it is able to optimize the spatial configuration of its atoms for greater stability.