280 citations · 1.7k across the 60 of their papers we have counts for
14 papers · 1 filter
Supercm: Revisiting Clustering for Semi-Supervised Learning
Durgesh Singh, Ahcene Boubekki, Robert Jenssen +1
The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often…
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders
Rogelio A Mancisidor, Robert Jenssen, Shujian Yu +1
Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixtu…
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Shujian Yu, Xi Yu, Sigurd Løkse +2
The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum suf…
The Conditional Cauchy-Schwarz Divergence with Applications to Time-Series Data and Sequential Decision Making
Shujian Yu, Hongming Li, Sigurd Løkse +2
The Cauchy-Schwarz (CS) divergence was developed by Príncipe et al. in 2000. In this paper, we extend the classic CS divergence to quantify the closeness between two conditional di…
ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model
Srishti Gautam, Ahcene Boubekki, Stine Hansen +4
The need for interpretable models has fostered the development of self-explainable classifiers. Prior approaches are either based on multi-stage optimization schemes, impacting the…
Principle of Relevant Information for Graph Sparsification
Shujian Yu, Francesco Alesiani, Wenzhe Yin +2
Graph sparsification aims to reduce the number of edges of a graph while maintaining its structural properties. In this paper, we propose the first general and effective informatio…
Discriminative Multimodal Learning via Conditional Priors in Generative Models
Rogelio A. Mancisidor, Michael Kampffmeyer, Kjersti Aas +1
Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can,…
This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation
Srishti Gautam, Marina M. -C. Höhne, Stine Hansen +2
Current machine learning models have shown high efficiency in solving a wide variety of real-world problems. However, their black box character poses a major challenge for the unde…
On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit
Óscar Escudero-Arnanz, Joaquín Rodríguez-Álvarez, Karl Øyvind Mikalsen +2
The acquisition of Antimicrobial Multidrug Resistance (AMR) in patients admitted to the Intensive Care Units (ICU) is a major global concern. This study analyses data in the form o…
Measuring Dependence with Matrix-based Entropy Functional
Shujian Yu, Francesco Alesiani, Xi Yu +2
Measuring the dependence of data plays a central role in statistics and machine learning. In this work, we summarize and generalize the main idea of existing information-theoretic…
Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series
Kristoffer Wickstrøm, Karl Øyvind Mikalsen, Michael Kampffmeyer +2
Deep learning-based support systems have demonstrated encouraging results in numerous clinical applications involving the processing of time series data. While such systems often a…
Deep Image Translation with an Affinity-Based Change Prior for Unsupervised Multimodal Change Detection
Luigi Tommaso Luppino, Michael Kampffmeyer, Filippo Maria Bianchi +4
Image translation with convolutional neural networks has recently been used as an approach to multimodal change detection. Existing approaches train the networks by exploiting supe…
Time series cluster kernels to exploit informative missingness and incomplete label information
Karl Øyvind Mikalsen, Cristina Soguero-Ruiz, Filippo Maria Bianchi +2
The time series cluster kernel (TCK) provides a powerful tool for analysing multivariate time series subject to missing data. TCK is designed using an ensemble learning approach in…
Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
Shujian Yu, Kristoffer Wickstrøm, Robert Jenssen +1
The matrix-based Renyi's α-entropy functional and its multivariate extension were recently developed in terms of the normalized eigenspectrum of a Hermitian matrix of the projected…