Bulat Ibragimov — accepted AI-conference papers

2024

Finding NEM-U: Explaining unsupervised representation learning through neural network generated explanation masks

Bjørn Leth Møller, Christian Igel, Kristoffer Knutsen Wickstrøm, Jon Sporring, Robert Jenssen, Bulat Ibragimov

ICML 2024poster

Unsupervised representation learning has become an important ingredient of today's deep learning systems. However, only a few methods exist that explain a learned vector embedding in the sense of providing information about which parts of an input are the most important for its representation. These…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Cross-Modal Conceptualization in Bottleneck Models

Danis Alukaev, Semen Kiselev, Ilya Pershin, Bulat Ibragimov, Vladimir V. Ivanov, Alexey Kornaev +1

EMNLP 2023long main

Concept Bottleneck Models (CBMs) assume that training examples (e.g., x-ray images) are annotated with high-level concepts (e.g., types of abnormalities), and perform classification by first predicting the concepts, followed by predicting the label relying on these concepts. However, the primary cha…

Cited by 0 Source ↗Scholar ↗

2019

Minimal Variance Sampling in Stochastic Gradient Boosting

Bulat Ibragimov, Gleb Gusev

NeurIPS 2019poster

Stochastic Gradient Boosting (SGB) is a widely used approach to regularization of boosting models based on decision trees. It was shown that, in many cases, random sampling at each iteration can lead to better generalization performance of the model and can also decrease the learning time. Different…

Cited by 34 Source ↗PDF ↗code ↗Scholar ↗