Related papers: Towards Unsupervised Causal Representation Learnin…

In this paper, we investigate the algorithmic stability of unsupervised representation learning with deep generative models, as a function of repeated re-training on the same input data. Algorithms for learning low dimensional linear…

Anomaly detection is to identify samples that do not conform to the distribution of the normal data. Due to the unavailability of anomalous data, training a supervised deep neural network is a cumbersome task. As such, unsupervised methods…

In unsupervised ensemble learning, one obtains predictions from multiple sources or classifiers, yet without knowing the reliability and expertise of each source, and with no labeled data to assess it. The task is to combine these possibly…

Learning fair representation is crucial for achieving fairness or debiasing sensitive information. Most existing works rely on adversarial representation learning to inject some invariance into representation. However, adversarial learning…

Deep learning models struggle with compositional generalization, i.e. the ability to recognize or generate novel combinations of observed elementary concepts. In hopes of enabling compositional generalization, various unsupervised learning…

Unsupervised anomaly detection is a challenging task. Autoencoders (AEs) or generative models are often employed to model the data distribution of normal inputs and subsequently identify anomalous, out-of-distribution inputs by high…

We propose a new type of variational autoencoder to perform improved pre-processing for clustering and anomaly detection on data with a given label. Anomalies however are not known or labeled. We call our method conditional latent space…

Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events'…

Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions. Causal mediation analysis is a method that is often used to…

Most of the data-driven approaches applied to bearing fault diagnosis up to date are established in the supervised learning paradigm, which usually requires a large set of labeled data collected a priori. In practical applications, however,…

Generative data augmentation with latent diffusion models is a promising strategy for addressing class imbalance in medical imaging, yet current approaches focus on perceptual fidelity and domain-specific autoencoder fine-tuning while…

Identifying acoustic events from a continuously streaming audio source is of interest for many applications including environmental monitoring for basic research. In this scenario neither different event classes are known nor what…

Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…

This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. Our approach identifies both spurious and invariant latent features…

Disentanglement is a useful property in representation learning which increases the interpretability of generative models such as Variational autoencoders (VAE), Generative Adversarial Models, and their many variants. Typically in such…

Optimal computations under uncertainty require an adequate probabilistic representation about beliefs. Deep generative models, and specifically Variational Autoencoders (VAEs), have the potential to meet this demand by building latent…

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek…

Causal representation learning in the anti-causal setting (labels cause features rather than the reverse) presents unique challenges requiring specialized approaches. We propose Anti-Causal Invariant Abstractions (ACIA), a novel…

Masked autoencoders (MAEs) have established themselves as a powerful method for unsupervised pre-training for computer vision tasks. While vanilla MAEs put equal emphasis on reconstructing the individual parts of the image, we propose to…