English
Related papers

Related papers: Shortcut Detection with Variational Autoencoders

200 papers

Sparse autoencoders (SAEs) have emerged as a powerful tool for uncovering interpretable features in large language models (LLMs) through the sparse directions they learn. However, the sheer number of extracted directions makes comprehensive…

Computation and Language · Computer Science 2025-11-11 Xinyuan Yan , Shusen Liu , Kowshik Thopalli , Bei Wang

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

Benchmark datasets play an important role in evaluating Natural Language Understanding (NLU) models. However, shortcuts -- unwanted biases in the benchmark datasets -- can damage the effectiveness of benchmark datasets in revealing models'…

Human-Computer Interaction · Computer Science 2023-01-16 Zhihua Jin , Xingbo Wang , Furui Cheng , Chunhui Sun , Qun Liu , Huamin Qu

Deep-learning models can extract a rich assortment of features from data. Which features a model uses depends not only on \emph{predictivity} -- how reliably a feature indicates training-set labels -- but also on \emph{availability} -- how…

Machine Learning · Computer Science 2024-07-15 Katherine L. Hermann , Hossein Mobahi , Thomas Fel , Michael C. Mozer

Learning from heterogeneous data poses challenges such as combining data from various sources and of different types. Meanwhile, heterogeneous data are often associated with missingness in real-world applications due to heterogeneity and…

Machine Learning · Computer Science 2021-02-26 Yu Gong , Hossein Hajimirsadeghi , Jiawei He , Thibaut Durand , Greg Mori

The Variational Autoencoder (VAE) has proven to be an effective model for producing semantically meaningful latent representations for natural data. However, it has thus far seen limited application to sequential data, and, as we…

Machine Learning · Computer Science 2019-11-12 Adam Roberts , Jesse Engel , Colin Raffel , Curtis Hawthorne , Douglas Eck

Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent…

Machine Learning · Statistics 2026-04-02 Veranika Boukun , Jörg Lücke

Variational Autoencoders (VAE) are widely used for dimensionality reduction of large-scale tabular and image datasets, under the assumption of independence between data observations. In practice, however, datasets are often correlated, with…

Machine Learning · Statistics 2024-12-25 Giora Simchoni , Saharon Rosset

We present the development of a semi-supervised regression method using variational autoencoders (VAE), which is customized for use in soft sensing applications. We motivate the use of semi-supervised learning considering the fact that…

Machine Learning · Computer Science 2022-12-12 Yilin Zhuang , Zhuobin Zhou , Burak Alakent , Mehmet Mercangöz

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…

Data Analysis, Statistics and Probability · Physics 2025-08-18 Alexander Yue , Haoyi Jia , Julia Gonski

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM)…

Computation and Language · Computer Science 2025-02-04 Daniel Pluth , Yu Zhou , Vijay K. Gurbani

Model-agnostic anomaly detection is one of the promising approaches in the search for new beyond the standard model physics. In this paper, we present Set-VAE, a particle-based variational autoencoder (VAE) anomaly detection algorithm. We…

High Energy Physics - Experiment · Physics 2023-11-30 Ryan Liu , Abhijith Gandrakota , Jennifer Ngadiuba , Maria Spiropulu , Jean-Roch Vlimant

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,…

Machine Learning · Computer Science 2019-12-10 Shen Zhang , Fei Ye , Bingnan Wang , Thomas G. Habetler

Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Andrew Kiruluta

Learning interpretable and disentangled representations of data is a key topic in machine learning research. Variational Autoencoder (VAE) is a scalable method for learning directed latent variable models of complex data. It employs a clear…

Machine Learning · Computer Science 2020-06-04 Andriy Serdega , Dae-Shik Kim

Unsupervised anomaly detection could be crucial in future analyses searching for rare phenomena in large datasets, as for example collected at the LHC. To this end, we introduce a physics inspired variational autoencoder (VAE) architecture…

High Energy Physics - Phenomenology · Physics 2022-06-08 Blaž Bortolato , Barry M. Dillon , Jernej F. Kamenik , Aleks Smolkovič

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially…

Image and Video Processing · Electrical Eng. & Systems 2020-01-03 David Zimmerer , Simon Kohl , Jens Petersen , Fabian Isensee , Klaus Maier-Hein

Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number and nature of fault…

Machine Learning · Computer Science 2020-10-01 Manuel Arias Chao , Bryan T. Adey , Olga Fink

Variational Autoencoders (VAEs) are powerful generative models that have been widely used in various fields, including image and text generation. However, one of the known challenges in using VAEs is the model's sensitivity to its…

Machine Learning · Computer Science 2024-12-31 Gabriela Sejnova , Michal Vavrecka , Karla Stepanova