110 citations · 138 across the 14 of their papers we have counts for
16 papers
Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen +1
Recently, several methods have leveraged deep generative modeling to produce example-based explanations of image classifiers. Despite producing visually stunning results, these met…
GradCheck: Analyzing classifier guidance gradients for conditional diffusion sampling
Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen +1
To sample from an unconditionally trained Denoising Diffusion Probabilistic Model (DDPM), classifier guidance adds conditional information during sampling, but the gradients from c…
Diffusion-based Visual Counterfactual Explanations -- Towards Systematic Quantitative Evaluation
Philipp Vaeth, Alexander M. Fruehwald, Benjamin Paassen +1
Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality.…
Discrete Graph Auto-Encoder
Yoann Boget, Magda Gregorova, Alexandros Kalousis
Despite advances in generative methods, accurately modeling the distribution of graphs remains a challenging task primarily because of the absence of predefined or inherent unique…
GrannGAN: Graph annotation generative adversarial networks
Yoann Boget, Magda Gregorova, Alexandros Kalousis
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton. Th…
Permutation Equivariant Generative Adversarial Networks for Graphs
Yoann Boget, Magda Gregorova, Alexandros Kalousis
One of the most discussed issues in graph generative modeling is the ordering of the representation. One solution consists of using equivariant generative functions, which ensure t…
Learned transform compression with optimized entropy encoding
Magda Gregorová, Marc Desaules, Alexandros Kalousis
We consider the problem of learned transform compression where we learn both, the transform as well as the probability distribution over the discrete codes. We utilize a soft relax…
Improving VAE generations of multimodal data through data-dependent conditional priors
Frantzeska Lavda, Magda Gregorová, Alexandros Kalousis
One of the major shortcomings of variational autoencoders is the inability to produce generations from the individual modalities of data originating from mixture distributions. Thi…
Sparse Learning for Variable Selection with Structures and Nonlinearities
Magda Gregorova
In this thesis we discuss machine learning methods performing automated variable selection for learning sparse predictive models. There are multiple reasons for promoting sparsity…
Continual Classification Learning Using Generative Models
Frantzeska Lavda, Jason Ramapuram, Magda Gregorova +1
Continual learning is the ability to sequentially learn over time by accommodating knowledge while retaining previously learned experiences. Neural networks can learn multiple task…
Structured nonlinear variable selection
Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet
We investigate structured sparsity methods for variable selection in regression problems where the target depends nonlinearly on the inputs. We focus on general nonlinear functions…
Large-scale Nonlinear Variable Selection via Kernel Random Features
Magda Gregorová, Jason Ramapuram, Alexandros Kalousis +1
We propose a new method for input variable selection in nonlinear regression. The method is embedded into a kernel regression machine that can model general nonlinear functions, no…
Learning Predictive Leading Indicators for Forecasting Time Series Systems with Unknown Clusters of Forecast Tasks
Magda Gregorova, Alexandros Kalousis, Stephane Marchand-Maillet
We present a new method for forecasting systems of multiple interrelated time series. The method learns the forecast models together with discovering leading indicators from within…
Forecasting and Granger Modelling with Non-linear Dynamical Dependencies
Magda Gregorová, Alexandros Kalousis, Stéphane Marchand-Maillet
Traditional linear methods for forecasting multivariate time series are not able to satisfactorily model the non-linear dependencies that may exist in non-Gaussian series. We build…
Lifelong Generative Modeling
Jason Ramapuram, Magda Gregorova, Alexandros Kalousis
Lifelong learning is the problem of learning multiple consecutive tasks in a sequential manner, where knowledge gained from previous tasks is retained and used to aid future learni…
Learning Leading Indicators for Time Series Predictions
Magda Gregorova, Alexandros Kalousis, Stéphane Marchand-Maillet
We consider the problem of learning models for forecasting multiple time-series systems together with discovering the leading indicators that serve as good predictors for the syste…