English
Related papers

Related papers: Learning Invariances for Interpretability using Su…

200 papers

Exemplar-based methods rely on informative data points or prototypes to guide the optimization of learning algorithms. Such data facilitate interpretable model design and prediction. Of particular interest is the utility of exemplars in…

Machine Learning · Computer Science 2022-11-22 Priya Mani , Carlotta Domeniconi

We investigate the problem of learning representations that are invariant to certain nuisance or sensitive factors of variation in the data while retaining as much of the remaining information as possible. Our model is based on a…

Machine Learning · Statistics 2017-08-11 Christos Louizos , Kevin Swersky , Yujia Li , Max Welling , Richard Zemel

Machine learning methods often need a large amount of labeled training data. Since the training data is assumed to be the ground truth, outliers can severely degrade learned representations and performance of trained models. Here we apply…

Machine Learning · Statistics 2019-12-24 Haleh Akrami , Anand A. Joshi , Jian Li , Sergul Aydore , Richard M. Leahy

Learning data representations that capture task-related features, but are invariant to nuisance variations remains a key challenge in machine learning. We introduce an automated Bayesian inference framework, called AutoBayes, that explores…

Machine Learning · Computer Science 2020-12-01 Andac Demir , Toshiaki Koike-Akino , Ye Wang , Deniz Erdogmus

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…

Computation and Language · Computer Science 2018-11-02 Yijun Xiao , Tiancheng Zhao , William Yang Wang

Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold. In this paper, we propose a novel representation learning algorithm which combines the…

Machine Learning · Computer Science 2021-07-13 Fei Ye , Adrian G. Bors

Autoencoders are able to learn useful data representations in an unsupervised matter and have been widely used in various machine learning and computer vision tasks. In this work, we present methods to train Invertible Neural Networks…

Machine Learning · Computer Science 2023-03-22 The-Gia Leo Nguyen , Lynton Ardizzone , Ullrich Köthe

Machine learning is capable of discriminating phases of matter, and finding associated phase transitions, directly from large data sets of raw state configurations. In the context of condensed matter physics, most progress in the field of…

Statistical Mechanics · Physics 2017-12-06 Pedro Ponte , Roger G. Melko

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Machine Learning · Computer Science 2025-11-13 Ege Erdogan , Ana Lucic

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Machine Learning · Statistics 2022-05-31 Mingtian Zhang , Tim Z. Xiao , Brooks Paige , David Barber

Variational Autoencoders (VAEs) have been shown to be remarkably effective in recovering model latent spaces for several computer vision tasks. However, currently trained VAEs, for a number of reasons, seem to fall short in learning…

Machine Learning · Computer Science 2021-07-27 Chandrajit Bajaj , Avik Roy , Haoran Zhang

In recent years, extending variational autoencoder's framework to learn disentangled representations has received much attention. We address this problem by proposing a framework capable of disentangling class-related and class-independent…

Machine Learning · Computer Science 2021-02-02 Sina Hajimiri , Aryo Lotfi , Mahdieh Soleymani Baghshah

In self-supervised learning, a model is trained to solve a pretext task, using a data set whose annotations are created by a machine. The objective is to transfer the trained weights to perform a downstream task in the target domain. We…

Machine Learning · Computer Science 2021-10-22 Prathamesh Sonawane , Sparsh Drolia , Saqib Shamsi , Bhargav Jain

The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space. However, on discrete data such as text, it is unclear…

Computation and Language · Computer Science 2020-08-10 Peng Xu , Jackie Chi Kit Cheung , Yanshuai Cao

The ability to record activities from hundreds of neurons simultaneously in the brain has placed an increasing demand for developing appropriate statistical techniques to analyze such data. Recently, deep generative models have been…

Machine Learning · Statistics 2020-11-11 Ding Zhou , Xue-Xin Wei

The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative…

Machine-learning models have demonstrated a great ability to learn complex patterns and make predictions. In high-dimensional nonlinear problems of fluid dynamics, data representation often greatly affects the performance and…

Fluid Dynamics · Physics 2022-07-29 Runze Li , Yufei Zhang , Haixin Chen

Variational Autoencoders (VAEs) have gained significant popularity among researchers as a powerful tool for understanding unknown distributions based on limited samples. This popularity stems partly from their impressive performance and…

Machine Learning · Computer Science 2024-02-27 Saptarshi Chakraborty , Peter L. Bartlett

Using a discriminative representation obtained by supervised deep learning methods showed promising results on diverse Content-Based Image Retrieval (CBIR) problems. However, existing methods exploiting labels during training try to…

Computer Vision and Pattern Recognition · Computer Science 2023-04-25 Mehdi Rafiei , Alexandros Iosifidis

Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However,…

Computer Vision and Pattern Recognition · Computer Science 2019-11-18 Matthew J. Vowels , Necati Cihan Camgoz , Richard Bowden