A Showcase of the Use of Autoencoders in Feature Learning Applications
Andalusian Research Institute in Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；Universidad de Granada（格拉纳达大学）；Universidad de Jaén（哈恩大学）
David Charte, Francisco Charte, María J. del Jesus, Francisco Herrera
Autoencoders are techniques for data representation learning based on artificial neural networks. Differently to other feature learning methods which may be focused on finding specific transformations of the feature space, they can be adapted to fulfill many purposes, such as data visualization, denoising, anomaly detection and semantic hashing. This work presents these applications and provides details on how autoencoders can perform them, including code samples making use of an R package with an easy-to-use interface for autoencoder design and training, \texttt{ruta}. Along the way, the explanations on how each learning task has been achieved are provided with the aim to help the reader design their own autoencoders for these or other objectives.
University of Trieste（特里埃斯特大学）；Abdus Salam International Centre for Theoretical Physics (ICTP)（阿布杜斯·萨拉姆国际理论物理学中心（ICTP））；Scuola Internazionale Superiore di Studi Avanzati (SISSA)（国际先进研究高等学院（SISSA））；University of Nova Gorica（诺瓦戈里察大学）；INFN – National Institute for Nuclear Physics（意大利国家核物理研究所（INFN））；ICSC - Centro Nazionale di Ricerca in High Performance Computing（高性能计算国家研究中心（ICSC））；Imperial College London（伦敦帝国理工学院）
Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to time-varying and time-invariant factors. In contrast, we consider multifactor disentanglement in which multiple (more than two) semantic disentangled components are generated. Key to our approach is a strong inductive bias where we assume that the underlying dynamics can be represented linearly in the latent space. Under this assumption, it becomes natural to exploit…
Indraprastha Institute of Information Technology（因德拉普拉斯信息技术学院）
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). W…
Imperial College London（帝国理工学院）；Jean le Rond d’Alembert Institute（让·勒朗·达朗贝尔研究所）；CNRS（法国国家科学研究中心）；Sorbonne University（索邦大学）；ONERA（法国国家航空航天研究院）；Université Paris Saclay（巴黎萨克雷大学）
Nonlinear principal component analysis (NLPCA) via autoencoders has attracted attention in the dynamical systems community due to its larger compression rate when compared to linear principal component analysis (PCA). These model reduction methods experience an increase in the dimensionality of the latent space when applied to datasets that exhibit invariant samples due to the presence of symmetries. In this study, we introduce a novel machine learning embedding for autoencoders, which uses Siamese networks and spatial transformer networks to account for discrete and continuous symmetries, res…
Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by constraining the weights in the encoder part, which maps input into hidden nodes and affects the generation of features. In this study, we show that a constraint to the decoder can also significantly improve its performance because the decoder determines how the latent variables contribute to the reconstruction of input. Inspired by the structural modal analysis…
Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predicti…
We present a representation learning method that learns features at multiple different levels of scale. Working within the unsupervised framework of denoising autoencoders, we observe that when the input is heavily corrupted during training, the network tends to learn coarse-grained features, whereas when the input is only slightly corrupted, the network tends to learn fine-grained features. This motivates the scheduled denoising autoencoder, which starts with a high level of noise that lowers as training progresses. We find that the resulting representation yields a significant boost on a lat…
Hefei University of Technology（合肥工业大学）；Yangzhou University（扬州大学）
Domain adaptation aims to exploit the knowledge in source domain to promote the learning tasks in target domain, which plays a critical role in real-world applications. Recently, lots of deep learning approaches based on autoencoders have achieved a significance performance in domain adaptation. However, most existing methods focus on minimizing the distribution divergence by putting the source and target data together to learn global feature representations, while they do not consider the local relationship between instances in the same category from different domains. To address this problem…
Machine learning models work better when curated features are provided to them. Feature engineering methods have been usually used as a preprocessing step to obtain or build a proper feature set. In late years, autoencoders (a specific type of symmetrical neural network) have been widely used to perform representation learning, proving their competitiveness against classical feature engineering algorithms. The main obstacle in the use of autoencoders is finding a good architecture, a process that most experts confront manually. An automated autoencoder architecture search procedure, based on e…
Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predicti…
Ecole Normale Supérieure（巴黎高等师范学院）；EPFL（洛桑联邦理工学院）；International School of Advanced Studies (SISSA)（国际高等研究学院）
Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning. While a detailed understanding of the dynamics of linear autoencoders has recently been obtained, the study of non-linear autoencoders has been hindered by the technical difficulty of handling training data with non-trivial correlations - a fundamental prerequisite for feature extraction. Here, we study the dynamics of feature learning in non-linear, shallow autoencoders. We derive a set of asymptotically exact equations that describe the generalisation dynamics of…
Due to the issue that existing wireless sensor network (WSN)-based anomaly detection methods only consider and analyze temporal features, in this paper, a self-supervised learning-based anomaly node detection method based on an autoencoder is designed. This method integrates temporal WSN data flow feature extraction, spatial position feature extraction and intermodal WSN correlation feature extraction into the design of the autoencoder to make full use of the spatial and temporal information of the WSN for anomaly detection. First, a fully connected network is used to extract the temporal feat…
University of Louisville（路易斯维尔大学）；University of Social Science（社会科学大学）；Information Technology Institute（信息技术研究所）
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested on three standard image data sets and one text dataset. The results indicate that the nonnegativity constraint forces the autoencoder to learn features that amount to a part-based representation of data, while improving sparsity and…
Autoencoder-assisted Feature Ensemble Net for Incipient Faults
Institue of education, Tsinghua University（清华大学教育学院）；City University of Hong Kong（香港城市大学）；University of Electronic Science and Technology of China（电子科技大学）；Department of Automation, Tsinghua University（清华大学自动化系）
Harbin Institute of Technology（哈尔滨工业大学）；Nanyang Technological University（南洋理工大学）
Hyperspectral image (HSI) classification is a hot topic in the remote sensing community. This paper proposes a new framework of spectral-spatial feature extraction for HSI classification, in which for the first time the concept of deep learning is introduced. Specifically, the model of autoencoder is exploited in our framework to extract various kinds of features. First we verify the eligibility of autoencoder by following classical spectral information based classification and use autoencoders with different depth to classify hyperspectral image. Further in the proposed framework, we combine …
Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It trains a neural network to pinpoint informative features for global exploring of representability and for local excavating of diversity. Architecturally, FAE extends autoencoders by adding a one-to-one scoring layer and a small sub-neural network for feature selection in an unsupervised fashion. With such a concise architecture, FAE achieves state-of-the-art perf…
School of Microelectornics and Communication Engineering, Chongqing University（重庆大学微电子与通信工程学院）
Deep learning is a kind of feature learning method with strong nonliear feature transformation and becomes more and more important in many fields of artificial intelligence. Deep autoencoder is one representative method of the deep learning methods, and can effectively extract abstract the information of datasets. However, it does not consider the complementarity between the deep features and original features during deep feature transformation. Besides, it suffers from small sample problem. In order to solve these problems, a novel deep autoencoder - hybrid feature embedded stacked sparse aut…
We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is controlled by a trade off parameter, and we show on six benchmark datasets the optimum lies between two extremes: a set of smaller, independent autoencoders each with low capacity, versus a single monolithic encoding, outperforming an appropriate baseline. In the present paper we explore the special case of linear MAE, and derive an SVD-based algorithm which conve…
We take steps towards understanding the "posterior collapse (PC)" difficulty in variational autoencoders (VAEs),~i.e. a degenerate optimum in which the latent codes become independent of their corresponding inputs. We rely on calculus of variations and theoretically explore a few popular VAE models, showing that PC always occurs for non-parametric encoders and decoders. Inspired by the popular noise contrastive estimation algorithm, we propose NC-VAE where the encoder discriminates between the latent codes of real data and of some artificially generated noise, in addition to encouraging good d…
Beyond Activation Patterns: A Weight-Based Out-of-Context Explanation of Sparse Autoencoder Features
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University（通用人工智能国家重点实验室，智能科学与技术学院，北京大学）
University of Technology Sydney（悉尼科技大学）；The Children’s Hospital at Westmead（韦斯特米德儿童医院）；Queen’s University at Kingston（金斯顿女王大学）
Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental results of using original and new features. In this paper, we propose a Relation Autoencoder model considering both data features and their relationships. We also extend it to work with other major autoencoder models including Sparse Autoencoder, Denoising Autoencoder and Variat…
King’s College London（伦敦国王学院）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
Cancer is a complex disease with significant social and economic impact. Advancements in high-throughput molecular assays and the reduced cost for performing high-quality multi-omics measurements have fuelled insights through machine learning . Previous studies have shown promise on using multiple omic layers to predict survival and stratify cancer patients. In this paper, we developed a Supervised Autoencoder (SAE) model for survival-based multi-omic integration which improves upon previous work, and report a Concrete Supervised Autoencoder model (CSAE), which uses feature selection to jointl…
The health monitoring of chronic diseases is very important for people with movement disorders because of their limited mobility and long duration of chronic diseases. Machine learning-based processing of data collected from the human with movement disorders using wearable sensors is an effective method currently available for health monitoring. However, wearable sensor systems are difficult to obtain high-quality and large amounts of data, which cannot meet the requirement for diagnostic accuracy. Moreover, existing machine learning methods do not handle this problem well. Feature learning is…
Romanian Institute of Science and Technology（罗马尼亚科学技术研究院）；Technical University of Cluj-Napoca（克卢日-纳波卡技术大学）
In the present work we propose an unsupervised ensemble method consisting of oblique trees that can address the task of auto-encoding, namely Oblique Forest AutoEncoders (briefly OF-AE). Our method is a natural extension of the eForest encoder introduced in [1]. More precisely, by employing oblique splits consisting in multivariate linear combination of features instead of the axis-parallel ones, we will devise an auto-encoder method through the computation of a sparse solution of a set of linear inequalities consisting of feature values constraints. The code for reproducing our results is ava…
Reduced order modeling (ROM) is a field of techniques that approximates complex physics-based models of real-world processes by inexpensive surrogates that capture important dynamical characteristics with a smaller number of degrees of freedom. Traditional ROM techniques such as proper orthogonal decomposition (POD) focus on linear projections of the dynamics onto a set of spectral features. In this paper we explore the construction of ROM using autoencoders (AE) that perform nonlinear projections of the system dynamics onto a low dimensional manifold learned from data. The approach uses convo…
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The 63rd Research Institute, National University of Defense Technology, Nanjing（国防科技大学第六十三研究所，南京）
Multi-label (ML) classification is an actively researched topic currently, which deals with convoluted and overlapping boundaries that arise due to several labels being active for a particular data instance. We propose a classifier capable of extracting underlying features and introducing non-linearity to the data to handle the complex decision boundaries. A novel neural network model has been developed where the input features are subjected to two transformations adapted from multi-label functional link artificial neural network and autoencoders. First, a functional expansion of the original …
Efficient querying and retrieval of healthcare data is posing a critical challenge today with numerous connected devices continuously generating petabytes of images, text, and internet of things (IoT) sensor data. One approach to efficiently store the healthcare data is to extract the relevant and representative features and store only those features instead of the continuous streaming data. However, it raises a question as to the amount of information content we can retain from the data and if we can reconstruct the pseudo-original data when needed. By facilitating relevant and representative…
Disentangling Dense Embeddings with Sparse Autoencoders
The Australian National University（澳大利亚国立大学）；Stanford University（斯坦福大学）；Columbia University（哥伦比亚大学）；Space Telescope Science Institute（空间望远镜科学研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）
High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty. Feature selection which selects a subset from observed features is a widely used approach for improving performance and effectiveness of machine learning models with high-dimensional data. In this paper, we propose a novel AutoEncoder Feature Selector (AEFS) for unsupervised feature selection which combines autoencoder regression and group lasso tasks. Compared to traditional feature selection methods, AEFS can select the most important features by excavatin…
Ensemble Visualization With Variational Autoencoder
Institute of Medical Technology, Peking University Health Science Center（北京大学健康科学中心医学技术研究所）；National Institute of Health Data Science, Peking University（北京大学健康数据科学国家研究院）；Center for Machine Learning Research, Peking University（北京大学机器学习研究中心）
Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event discrimination (i.e., earthquake vs. noise waveforms, earthquake vs. explosion waveforms, and phase picking). These tests involve training an autoencoder, either undercomplete or overcomplete, on a large amount of earthquake waveforms, and then using the trained encoder as a feature extractor with s…
We introduce the concrete autoencoder, an end-to-end differentiable method for global feature selection, which efficiently identifies a subset of the most informative features and simultaneously learns a neural network to reconstruct the input data from the selected features. Our method is unsupervised, and is based on using a concrete selector layer as the encoder and using a standard neural network as the decoder. During the training phase, the temperature of the concrete selector layer is gradually decreased, which encourages a user-specified number of discrete features to be learned. Durin…
Pace University（佩斯大学）；Seidenberg School of CSIS（塞登伯格计算机科学与信息系统学院）
This paper explores using a Long short-term memory (LSTM) based sequence autoencoder to learn interesting features for detecting surveillance aircraft using ADS-B flight data. An aircraft periodically broadcasts ADS-B (Automatic Dependent Surveillance - Broadcast) data to ground receivers. The ability of LSTM networks to model varying length time series data and remember dependencies that span across events makes it an ideal candidate for implementing a sequence autoencoder for ADS-B data because of its possible variable length time series, irregular sampling and dependencies that span across …
