Otilia Stretcu
I am a Research Scientist at Google AI in Mountain View, California, working on machine learning research.
Previously, I was a PhD student in the Machine Learning Department at Carnegie Mellon University, co-advised by Tom Mitchell and Barnabàs Pòczos. My PhD research focused on developing algorithms for machine learning, mainly focused on semi-supervised learning, curriculum learning, multitask learning, and graph-based problems. I am also passionate about applying machine learning methods in neuroscience, in order to study how the brain understands language and controls speech. Previously, I did some research in Computer Vision, with the goal of detecting and tracking objects in videos.
Research Areas
Authored Publications
Google Publications
Other Publications
Sort By
Graph Agreement Models for Semi-supervised Learning
Krishnamurthy Viswanathan
Anthony Platanios
Sujith Ravi
Proceedings of the Thirty-third Conference on Neural Information Processing Systems, Neurips 2019
Preview abstract
Graph-based algorithms are among the most successful paradigms for solving semi-supervised learning tasks. Recent work on graph convolutional networks and neural graph learning methods has successfully combined the expressiveness of neural networks with graph structures. We propose a technique that, when applied to these methods, achieves state-of-the-art results on semi-supervised learning datasets. Traditional graph-based algorithms, such as label propagation, were designed with the underlying assumption that the label of a node can be imputed from that of the neighboring nodes. However, real-world graphs are either noisy or have edges that do not correspond to label agreement. To address this, we propose Graph Agreement Models (GAM), which introduces an auxiliary model that predicts the probability of two nodes sharing the same label as a learned function of their features. The agreement model is used when training a node classification model by encouraging agreement only for the pairs of nodes it deems likely to have the same label, thus guiding its parameters to better local optima. The classification and agreement models are trained jointly in a co-training fashion. Moreover, GAM can also be applied to any semi-supervised classification problem, by inducing a graph whenever one is not provided. We demonstrate that our method achieves a relative improvement of up to 72% for various node classification models, and obtains state-of-the-art results on multiple established datasets.
View details
No Results Found