4 citations · 8 across the 20 of their papers we have counts for
7 papers · 1 filter
Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
Alba Carballo-Castro, Sonia Laguna, Moritz Vandenhirtz +1
Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are gen…
TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusion
Jorge da Silva Gonçalves, Laura Manduchi, Moritz Vandenhirtz +1
Generative modeling and clustering are conventionally distinct tasks in machine learning. Variational Autoencoders (VAEs) have been widely explored for their ability to integrate b…
From Logits to Hierarchies: Hierarchical Clustering made Simple
Emanuele Palumbo, Moritz Vandenhirtz, Alain Ryser +2
The hierarchical structure inherent in many real-world datasets makes the modeling of such hierarchies a crucial objective in both unsupervised and supervised machine learning. Whi…
Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
Jorge da Silva Goncalves, Laura Manduchi, Moritz Vandenhirtz +1
This paper introduces Diffuse-TreeVAE, a deep generative model that integrates hierarchical clustering into the framework of Denoising Diffusion Probabilistic Models (DDPMs). The p…
scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data
Moritz Vandenhirtz, Florian Barkmann, Laura Manduchi +2
We propose a novel method, scTree, for single-cell Tree Variational Autoencoders, extending a hierarchical clustering approach to single-cell RNA sequencing data. scTree corrects f…
Stochastic Concept Bottleneck Models
Moritz Vandenhirtz, Sonia Laguna, Ričards Marcinkevičs +1
Concept Bottleneck Models (CBMs) have emerged as a promising interpretable method whose final prediction is based on intermediate, human-understandable concepts rather than the raw…
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
Sonia Laguna, Ričards Marcinkevičs, Moritz Vandenhirtz +1
Recently, interpretable machine learning has re-explored concept bottleneck models (CBM). An advantage of this model class is the user's ability to intervene on predicted concept v…