36 citations · 173 across the 61 of their papers we have counts for
19 papers · 1 filter
Mixture of Experts Distributional Regression: Implementation Using Robust Estimation with Adaptive First-order Methods
David Rügamer, Florian Pfisterer, Bernd Bischl +1
In this work, we propose an efficient implementation of mixtures of experts distributional regression models which exploits robust estimation by using stochastic first-order optimi…
Improved proteasomal cleavage prediction with positive-unlabeled learning
Emilio Dorigatti, Bernd Bischl, Benjamin Schubert
Accurate in silico modeling of the antigen processing pathway is crucial to enable personalized epitope vaccine design for cancer. An important step of such pathway is the degradat…
What cleaves? Is proteasomal cleavage prediction reaching a ceiling?
Ingo Ziegler, Bolei Ma, Ercong Nie +4
Epitope vaccines are a promising direction to enable precision treatment for cancer, autoimmune diseases, and allergies. Effectively designing such vaccines requires accurate predi…
Joint Debiased Representation and Image Clustering Learning with Self-Supervision
Shunjie-Fabian Zheng, JaeEun Nam, Emilio Dorigatti +3
Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the le…
Robust and Efficient Imbalanced Positive-Unlabeled Learning with Self-supervision
Emilio Dorigatti, Jonas Schweisthal, Bernd Bischl +1
Learning from positive and unlabeled (PU) data is a setting where the learner only has access to positive and unlabeled samples while having no information on negative examples. Su…
Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
Felix Ott, Nisha Lakshmana Raichur, David Rügamer +4
Visual-inertial localization is a key problem in computer vision and robotics applications such as virtual reality, self-driving cars, and aerial vehicles. The goal is to estimate…
Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
Andreas Klaß, Sven M. Lorenz, Martin W. Lauer-Schmaltz +4
For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for com…
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
Mehmet Ozgur Turkoglu, Alexander Becker, Hüseyin Anil Gündüz +6
The ability to estimate epistemic uncertainty is often crucial when deploying machine learning in the real world, but modern methods often produce overconfident, uncalibrated uncer…
Factorized Structured Regression for Large-Scale Varying Coefficient Models
David Rügamer, Andreas Bender, Simon Wiegrebe +4
Recommender Systems (RS) pervade many aspects of our everyday digital life. Proposed to work at scale, state-of-the-art RS allow the modeling of thousands of interactions and facil…
What Is Fairness? On the Role of Protected Attributes and Fictitious Worlds
Ludwig Bothmann, Kristina Peters, Bernd Bischl
A growing body of literature in fairness-aware machine learning (fairML) aims to mitigate machine learning (ML)-related unfairness in automated decision-making (ADM) by defining me…
Efficient Automated Deep Learning for Time Series Forecasting
Difan Deng, Florian Karl, Frank Hutter +2
Recent years have witnessed tremendously improved efficiency of Automated Machine Learning (AutoML), especially Automated Deep Learning (AutoDL) systems, but recent work focuses on…
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
Ashkan Khakzar, Yawei Li, Yang Zhang +5
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced. Training…
Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
Felix Ott, David Rügamer, Lucas Heublein +2
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this…
REPID: Regional Effect Plots with implicit Interaction Detection
Julia Herbinger, Bernd Bischl, Giuseppe Casalicchio
Machine learning models can automatically learn complex relationships, such as non-linear and interaction effects. Interpretable machine learning methods such as partial dependence…
DeepPAMM: Deep Piecewise Exponential Additive Mixed Models for Complex Hazard Structures in Survival Analysis
Philipp Kopper, Simon Wiegrebe, Bernd Bischl +2
Survival analysis (SA) is an active field of research that is concerned with time-to-event outcomes and is prevalent in many domains, particularly biomedical applications. Despite…
Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition
Felix Ott, David Rügamer, Lucas Heublein +2
Cross-modal representation learning learns a shared embedding between two or more modalities to improve performance in a given task compared to using only one of the modalities. Cr…
Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
Felix Ott, David Rügamer, Lucas Heublein +4
Purpose. Handwriting is one of the most frequently occurring patterns in everyday life and with it come challenging applications such as handwriting recognition (HWR), writer ident…
Marginal Effects for Non-Linear Prediction Functions
Christian A. Scholbeck, Giuseppe Casalicchio, Christoph Molnar +2
Beta coefficients for linear regression models represent the ideal form of an interpretable feature effect. However, for non-linear models and especially generalized linear models,…
Uncertainty-aware Pseudo-label Selection for Positive-Unlabeled Learning
Emilio Dorigatti, Jann Goschenhofer, Benjamin Schubert +2
Positive-unlabeled learning (PUL) aims at learning a binary classifier from only positive and unlabeled training data. Even though real-world applications often involve imbalanced…