Europe
Learning semantic similarity in a continuous space
Our work naturally extends Word Mover's Distance (WMD) [
dist(x,y) andavg(A,B) = 1 |A| |B| X
In this paper, we present a comprehensive study of the performance of average-link in metric spaces, regarding several natural criteria that capture separability and cohesion, and aremore interpretable than Dasgupta'scost function and itsvariants.
Online Reciprocal Recommendation with Theoretical Performance Guarantees
Claudio Gentile, Nikos Parotsidis, Fabio Vitale
Neural Information Processing Systems http://nips.cc/
Paradoxes in Fair Machine Learning
Paul Goelz, Anson Kahng, Ariel D. Procaccia
Neural Information Processing Systems http://nips.cc/
Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks
Aya Abdelsalam Ismail, Mohamed Gunady, Luiz Pessoa, Hector Corrada Bravo, Soheil Feizi
Neural Information Processing Systems http://nips.cc/
Explanations can be manipulated and geometry is to blame
Ann-Kathrin Dombrowski, Maximillian Alber, Christopher Anders, Marcel Ackermann, Klaus-Robert Müller, Pan Kessel
This allows us to derive an upper bound on the susceptibility of explanations to manipulations.
An Efficient Pruning Algorithm for Robust Isotonic Regression
Neural Information Processing Systems http://nips.cc/
