Search Results for author:
Found 42 papers, 29 papers with code
From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
Understanding the decision-making process of machine learning models provides valuable insights into the task, the data, and the reasons behind a model's failures.
Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathology
Vision foundation models (FMs) are accelerating the development of digital pathology algorithms and transforming biomedical research.
From Pixels to Components: Eigenvector Masking for Visual Representation Learning
We thus posit that predicting masked from visible components involves more high-level features, allowing our masking strategy to extract more useful representations.
Weakly-Supervised Multimodal Learning on MIMIC-CXR
Multimodal data integration and label scarcity pose significant challenges for machine learning in medical settings.
Automatic Classification of General Movements in Newborns
General movements (GMs) are spontaneous, coordinated body movements in infants that offer valuable insights into the developing nervous system.
Cross-Entropy Is All You Need To Invert the Data Generating Process
Second, we show that on DisLib, a widely-used disentanglement benchmark, simple classification tasks recover latent structures up to linear transformations.
Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable.
Hierarchical Clustering for Conditional Diffusion in Image Generation
This paper addresses this gap by introducing TreeDiffusion, a deep generative model that conditions Diffusion Models on hierarchical clusters to obtain high-quality, cluster-specific generations.
From Logits to Hierarchies: Hierarchical Clustering made Simple
The structure of many real-world datasets is intrinsically hierarchical, making the modeling of such hierarchies a critical objective in both unsupervised and supervised machine learning.
Structured Generations: Using Hierarchical Clusters to guide Diffusion Models
This paper introduces Diffuse-TreeVAE, a deep generative model that integrates hierarchical clustering into the framework of Denoising Diffusion Probabilistic Models (DDPMs).
Stochastic Concept Bottleneck Models
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 input.
scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data
We propose a novel method, scTree, for single-cell Tree Variational Autoencoders, extending a hierarchical clustering approach to single-cell RNA sequencing data.
Anomaly Detection by Context Contrasting
At test time, representations of anomalies that do not adhere to the invariances of normal data then deviate from their respective context cluster.
Self-Supervised Anomaly Detection
Self-Supervised Learning
+1
What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
Despite significant progress, evaluation of explainable artificial intelligence remains elusive and challenging.
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
Recently, interpretable machine learning has re-explored concept bottleneck models (CBM).
Benchmarking the Fairness of Image Upsampling Methods
Recent years have witnessed a rapid development of deep generative models for creating synthetic media, such as images and videos.
This Reads Like That: Deep Learning for Interpretable Natural Language Processing
Prototype learning, a popular machine learning method designed for inherently interpretable decisions, leverages similarities to learned prototypes for classifying new data.
On the Properties and Estimation of Pointwise Mutual Information Profiles
The pointwise mutual information profile, or simply profile, is the distribution of pointwise mutual information for a given pair of random variables.
M(otion)-mode Based Prediction of Ejection Fraction using Echocardiograms
Early detection of cardiac dysfunction through routine screening is vital for diagnosing cardiovascular diseases.
Beyond Normal: On the Evaluation of Mutual Information Estimators
Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology.
(Un)reasonable Allure of Ante-hoc Interpretability for High-stakes Domains: Transparency Is Necessary but Insufficient for Comprehensibility
Ante-hoc interpretability has become the holy grail of explainable artificial intelligence for high-stakes domains such as healthcare; however, this notion is elusive, lacks a widely-accepted definition and depends on the operational context.
Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss
We propose Signal is Harder (SiH), a variational-autoencoder-based method that simultaneously trains a biased and unbiased classifier using a novel, disentangling reweighting scheme inspired by the focal loss.
Differentiable Random Partition Models
Partitioning a set of elements into an unknown number of mutually exclusive subsets is essential in many machine learning problems.
Identifiability Results for Multimodal Contrastive Learning
Our work generalizes previous identifiability results by redefining the generative process in terms of distinct mechanisms with modality-specific latent variables.
Interpretable and intervenable ultrasonography-based machine learning models for pediatric appendicitis
Appendicitis is among the most frequent reasons for pediatric abdominal surgeries.
Introduction to Machine Learning for Physicians: A Survival Guide for Data Deluge
Many modern research fields increasingly rely on collecting and analysing massive, often unstructured, and unwieldy datasets.
On the Identifiability and Estimation of Causal Location-Scale Noise Models
We study the class of location-scale or heteroscedastic noise models (LSNMs), in which the effect $Y$ can be written as a function of the cause $X$ and a noise source $N$ independent of $X$, which may be scaled by a positive function $g$ over the cause, i. e., $Y = f(X) + g(X)N$.
Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods
In addition, we compare several intra- and post-processing approaches applied to debiasing deep chest X-ray classifiers.
Anomaly Detection in Echocardiograms with Dynamic Variational Trajectory Models
The introduced method takes advantage of the periodic nature of the heart cycle to learn three variants of a variational latent trajectory model (TVAE).
How Robust is Unsupervised Representation Learning to Distribution Shift?
As such, there is a lack of insight on the robustness of the representations learned from unsupervised methods, such as self-supervised learning (SSL) and auto-encoder based algorithms (AE), to distribution shift.
Learning Group Importance using the Differentiable Hypergeometric Distribution
We introduce reparameterizable gradients to learn the importance between groups and highlight the advantage of explicitly learning the size of subsets in two typical applications: weakly-supervised learning and clustering.
On the Limitations of Multimodal VAEs
Multimodal variational autoencoders (VAEs) have shown promise as efficient generative models for weakly-supervised data.
Deep Conditional Gaussian Mixture Model for Constrained Clustering
Constrained clustering has gained significant attention in the field of machine learning as it can leverage prior information on a growing amount of only partially labeled data.
A Deep Variational Approach to Clustering Survival Data
In this work, we study the problem of clustering survival data $-$ a challenging and so far under-explored task.
Generalized Multimodal ELBO
Multiple data types naturally co-occur when describing real-world phenomena and learning from them is a long-standing goal in machine learning research.
Interpretable Models for Granger Causality Using Self-explaining Neural Networks
Exploratory analysis of time series data can yield a better understanding of complex dynamical systems.
Interpretability and Explainability: A Machine Learning Zoo Mini-tour
In this review, we examine the problem of designing interpretable and explainable machine learning models.
Counterfactual Explanation
Explainable artificial intelligence
+1
Multimodal Generative Learning Utilizing Jensen-Shannon-Divergence
Learning from different data types is a long-standing goal in machine learning research, as multiple information sources co-occur when describing natural phenomena.
Generation of Differentially Private Heterogeneous Electronic Health Records
In this work, we explore using Generative Adversarial Networks to generate synthetic, heterogeneous EHRs with the goal of using these synthetic records in place of existing data sets for downstream classification tasks.
Unsupervised Extraction of Phenotypes from Cancer Clinical Notes for Association Studies
To demonstrate the utility of our approach, we perform an association study of clinical features with somatic mutation profiles from 4, 007 cancer patients and their tumors.
Probabilistic Clustering of Time-Evolving Distance Data
We present a novel probabilistic clustering model for objects that are represented via pairwise distances and observed at different time points.
