187 citations · 575 across the 29 of their papers we have counts for
7 papers · 1 filter
RPGAN: GANs Interpretability via Random Routing
Andrey Voynov, Artem Babenko
In this paper, we introduce Random Path Generative Adversarial Network (RPGAN) -- an alternative design of GANs that can serve as a tool for generative model analysis. While the la…
Towards Similarity Graphs Constructed by Deep Reinforcement Learning
Dmitry Baranchuk, Artem Babenko
Similarity graphs are an active research direction for the nearest neighbor search (NNS) problem. New algorithms for similarity graph construction are continuously being proposed a…
Beyond Vector Spaces: Compact Data Representation as Differentiable Weighted Graphs
Denis Mazur, Vage Egiazarian, Stanislav Morozov +1
Learning useful representations is a key ingredient to the success of modern machine learning. Currently, representation learning mostly relies on embedding data into Euclidean spa…
Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data
Sergei Popov, Stanislav Morozov, Artem Babenko
Nowadays, deep neural networks (DNNs) have become the main instrument for machine learning tasks within a wide range of domains, including vision, NLP, and speech. Meanwhile, in an…
Unsupervised Neural Quantization for Compressed-Domain Similarity Search
Stanislav Morozov, Artem Babenko
We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefi…
Relevance Proximity Graphs for Fast Relevance Retrieval
Stanislav Morozov, Artem Babenko
In plenty of machine learning applications, the most relevant items for a particular query should be efficiently extracted, while the relevance function is based on a highly-nonlin…