Magnet seminars are usually held in room B21 on Thursdays, 11am. Check below for upcoming seminars and potential changes of schedule/location. You may also import the Magnet seminars public feed into your favorite calendar app. For further information, contact Aurélien.
Thu, March 22, 2018
Where? Inria B21
Natural language processing
Learning to represent nodes of a graph in a homogeneous vector space has many applications, such as predicting labels associated with users or more generally any entity in a social graph, forecasting future values of interrelated time series, or recommending items to users in a collaborative filtering setting. Most approaches suppose that the representation is reduced to a single point, that is, that a representation is certain. Uncertainty can have various causes related to the lack of information (isolated nodes in the graph) or because of the contradiction between neighboring nodes (different labels). Our hypothesis is that, because of these different factors, training will result in learned representations with different confidence, and that this uncertainty is important for many inference problems. For that, we leverage Gaussian embeddings, which have been firstly proposed for learning word embeddings (Vilnis et al., 2015), and show that they are both easy to learn and successful in various tasks.
Thursday, March 22, 2018 - 11:00 to 12:00