We present an approach to semi-supervised learning based on an exponential family characterization. Our approach generalizes previous work on coupled priors for hybrid generative/discriminative models. Our model is more flexible and natural than previous approaches. Experimental results on several data sets show that our approach also performs better in practice.
College of Information Science & Technology（信息科学与技术学院）；The Pennsylvania State University（宾夕法尼亚州立大学）
Two novel deep hybrid architectures, the Deep Hybrid Boltzmann Machine and the Deep Hybrid Denoising Auto-encoder, are proposed for handling semi-supervised learning problems. The models combine experts that model relevant distributions at different levels of abstraction to improve overall predictive performance on discriminative tasks. Theoretical motivations and algorithms for joint learning for each are presented. We apply the new models to the domain of data-streams in work towards life-long learning. The proposed architectures show improved performance compared to a pseudo-labeled, drop-o…
Semi-supervised learning has received a lot of recent attention as it alleviates the need for large amounts of labelled data which can often be expensive, requires expert knowledge and be time consuming to collect. Recent developments in deep semi-supervised classification have reached unprecedented performance and the gap between supervised and semi-supervised learning is ever-decreasing. This improvement in performance has been based on the inclusion of numerous technical tricks, strong augmentation techniques and costly optimisation schemes with multi-term loss functions. We propose a new f…
Università di Genova（热那亚大学）；CNR - SPIN Genova（意大利国家研究委员会热那亚自旋研究所）
We introduce a hybrid approach to solar flare prediction, whereby a supervised regularization method is used to realize feature importance and an unsupervised clustering method is used to realize the binary flare/no-flare decision. The approach is validated against NOAA SWPC data.
Consider semi-supervised learning for classification, where both labeled and unlabeled data are available for training. The goal is to exploit both datasets to achieve higher prediction accuracy than just using labeled data alone. We develop a semi-supervised logistic learning method based on exponential tilt mixture models, by extending a statistical equivalence between logistic regression and exponential tilt modeling. We study maximum nonparametric likelihood estimation and derive novel objective functions which are shown to be Fisher consistent. We also propose regularized estimation and c…
Laboratoire Informatique d’Avignon（阿维尼翁计算机实验室）；Université d’Avignon et des Pays de Vaucluse（阿维尼翁与沃克吕兹地区大学）；INRIA（法国国家信息与自动化研究所）；LORIA（洛林计算机科学及其应用实验室）
This paper presents a new hybrid learning algorithm for unsupervised classification tasks. We combined Fuzzy c-means learning algorithm and a supervised version of Minimerror to develop a hybrid incremental strategy allowing unsupervised classifications. We applied this new approach to a real-world database in order to know if the information contained in unlabeled features of a Geographic Information System (GIS), allows to well classify it. Finally, we compared our results to a classical supervised classification obtained by a multilayer perceptron.
We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the standard BN, where the statistics are computed within each batch, EMAN, used in the teacher, updates its statistics by exponential moving average from the BN statistics of the student. This design reduces the intrinsic cross-sample dependency of BN and enhances the generalization of the teacher. EMAN improves strong baselines for self-supervised learning by…
This paper presents a recurrent hybrid model and training procedure for task-oriented dialogue systems based on Deep Recurrent Q-Networks (DRQN). The model copes with both tasks required for Dialogue Management: State Tracking and Decision Making. It is based on modeling Human-Machine interaction into a latent representation embedding an interaction context to guide the discussion. The model achieves greater performance, learning speed and robustness than a non-recurrent baseline. Moreover, results allow interpreting and validating the policy evolution and the latent representations informatio…
Sorbonne Université（索邦大学）；Conservatoire National des Arts et Métiers（法国国立工艺学院）
In this paper, we introduce a new model for leveraging unlabeled data to improve generalization performances of image classifiers: a two-branch encoder-decoder architecture called HybridNet. The first branch receives supervision signal and is dedicated to the extraction of invariant class-related representations. The second branch is fully unsupervised and dedicated to model information discarded by the first branch to reconstruct input data. To further support the expected behavior of our model, we propose an original training objective. It favors stability in the discriminative branch and co…
U.S. Naval Academy（美国海军学院）；Naval Research Laboratory（海军研究实验室）
Many classification problems involve data instances that are interlinked with each other, such as webpages connected by hyperlinks. Techniques for "collective classification" (CC) often increase accuracy for such data graphs, but usually require a fully-labeled training graph. In contrast, we examine how to improve the semi-supervised learning of CC models when given only a sparsely-labeled graph, a common situation. We first describe how to use novel combinations of classifiers to exploit the different characteristics of the relational features vs. the non-relational features. We also extend …
Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised methods applied to the labeled training set alone. Effective SSL imposes structural assumptions on the data, e.g. that neighbors are more likely to share a classification or that the decision boundary lies in an area of low density. For complex and high-dimensional data, neural networks can learn feature embeddings to which traditional SSL methods can then b…
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Northrop Grumman Corporation（诺斯罗普·格鲁曼公司）；California NanoSystems Institute（加州纳米系统研究所）
From higher computational efficiency to enabling the discovery of novel and complex structures, deep learning has emerged as a powerful framework for the design and optimization of nanophotonic circuits and components. However, both data-driven and exploration-based machine learning strategies have limitations in their effectiveness for nanophotonic inverse design. Supervised machine learning approaches require large quantities of training data to produce high-performance models and have difficulty generalizing beyond training data given the complexity of the design space. Unsupervised and rei…
College of Information and Computer Sciences, University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校信息与计算机科学学院）
In supervised clustering, standard techniques for learning a pairwise dissimilarity function often suffer from a discrepancy between the training and clustering objectives, leading to poor cluster quality. Rectifying this discrepancy necessitates matching the procedure for training the dissimilarity function to the clustering algorithm. In this paper, we introduce a method for training the dissimilarity function in a way that is tightly coupled with hierarchical clustering, in particular single linkage. However, the appropriate clustering algorithm for a given dataset is often unknown. Thus we…
Semi supervised learning methods have gained importance in today's world because of large expenses and time involved in labeling the unlabeled data by human experts. The proposed hybrid approach uses SVM and Label Propagation to label the unlabeled data. In the process, at each step SVM is trained to minimize the error and thus improve the prediction quality. Experiments are conducted by using SVM and logistic regression(Logreg). Results prove that SVM performs tremendously better than Logreg. The approach is tested using 12 datasets of different sizes ranging from the order of 1000s to the or…
Due to the lack of expertise for medical image annotation, the investigation of label-efficient methodology for medical image segmentation becomes a heated topic. Recent progresses focus on the efficient utilization of weak annotations together with few strongly-annotated labels so as to achieve comparable segmentation performance in many unprofessional scenarios. However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances, which inevitably leads to perfo…
In this paper, we propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Various tasks for classifying new species from image data can be modeled as a semi-supervised few-shot classification, which assumes a labeled and unlabeled training examples and a small support set of the target classes. Predicting target classes with a few support examples per class makes the learning task difficult for existing semi-supervised classification methods, including selftraining, which iteratively est…
Exploring a Hybrid Deep Learning Approach for Anomaly Detection in Mental Healthcare Provider Billing: Addressing Label Scarcity through Semi-Supervised Anomaly Detection
Informatics Institute, University of Amsterdam（阿姆斯特丹大学信息学院）；Department of Computer Science and Technology, SUNY Empire State University（SUNY埃默里州立大学计算机科学与技术系）
Eindhoven University of Technology（埃因霍温理工大学）；Shandong University of Science and Technology（山东科技大学）；Philips Research（飞利浦研究院）
Catheter segmentation in 3D ultrasound is important for computer-assisted cardiac intervention. However, a large amount of labeled images are required to train a successful deep convolutional neural network (CNN) to segment the catheter, which is expensive and time-consuming. In this paper, we propose a novel catheter segmentation approach, which requests fewer annotations than the supervised learning method, but nevertheless achieves better performance. Our scheme considers a deep Q learning as the pre-localization step, which avoids voxel-level annotation and which can efficiently localize t…
Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates
School of Information Management and Mathematics, Jiangxi University of Finance and Economics（江西财经大学信息管理与数学学院）；School of Mathematics and Computer Science, Nanchang University（南昌大学数学与计算机科学学院）；Institute of Metaverse, Nanchang University（南昌大学元宇宙研究院）；Jiangxi Provincial Key Laboratory of Virtual Reality（江西省虚拟现实重点实验室）
Monash University（莫纳什大学）；Sun Yat-sen University（中山大学）；DarkMatter AI Research（DarkMatter AI研究院）；University of Oxford（牛津大学）；Alibaba Group（阿里巴巴集团）；RMIT University（皇家墨尔本理工大学）
A myriad of recent breakthroughs in hand-crafted neural architectures for visual recognition have highlighted the urgent need to explore hybrid architectures consisting of diversified building blocks. Meanwhile, neural architecture search methods are surging with an expectation to reduce human efforts. However, whether NAS methods can efficiently and effectively handle diversified search spaces with disparate candidates (e.g. CNNs and transformers) is still an open question. In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method t…
This Paper represents a literature review of Swarm intelligence algorithm in the area of semi-supervised classification. There are many research papers for applying swarm intelligence algorithms in the area of machine learning. Some algorithms of SI are applied in the area of ML either solely or hybrid with other ML algorithms. SI algorithms are also used for tuning parameters of ML algorithm, or as a backbone for ML algorithms. This paper introduces a brief literature review for applying swarm intelligence algorithms in the field of semi-supervised learning
In this work we show that Evolution Strategies (ES) are a viable method for learning non-differentiable parameters of large supervised models. ES are black-box optimization algorithms that estimate distributions of model parameters; however they have only been used for relatively small problems so far. We show that it is possible to scale ES to more complex tasks and models with millions of parameters. While using ES for differentiable parameters is computationally impractical (although possible), we show that a hybrid approach is practically feasible in the case where the model has both diffe…
Robust Millimeter Beamforming via Self-Supervised Hybrid Deep Learning
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；National and Kapodistrian University of Athens（雅典国立卡波迪斯特里亚大学）；School of Electrical and Electronics Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Khalifa University of Science and Technology（哈利法科技大学）
Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance
Artificial Intelligence Lab — Vrije Universiteit Brussel（自由大学布鲁塞尔人工智能实验室）；College of Science and Engineering — University of Galway（盖尔威大学科学与工程学院）；Family Medicine and Population Health — University of Antwerp（安特卫普大学家庭医学与人口健康）
Automatic segmentation of vertebral bodies (VBs) and intervertebral discs (IVDs) in 3D magnetic resonance (MR) images is vital in diagnosing and treating spinal diseases. However, segmenting the VBs and IVDs simultaneously is not trivial. Moreover, problems exist, including blurry segmentation caused by anisotropy resolution, high computational cost, inter-class similarity and intra-class variability, and data imbalances. We proposed a two-stage algorithm, named semi-supervised hybrid spine network (SSHSNet), to address these problems by achieving accurate simultaneous VB and IVD segmentation.…
Czestochowa University of Technology（琴斯托霍瓦理工大学）；Uber Technologies（优步科技公司）
This work presents a hybrid and hierarchical deep learning model for mid-term load forecasting. The model combines exponential smoothing (ETS), advanced Long Short-Term Memory (LSTM) and ensembling. ETS extracts dynamically the main components of each individual time series and enables the model to learn their representation. Multi-layer LSTM is equipped with dilated recurrent skip connections and a spatial shortcut path from lower layers to allow the model to better capture long-term seasonal relationships and ensure more efficient training. A common learning procedure for LSTM and ETS, with …
Facebook；Czestochowa University of Technology（琴斯托霍瓦技术大学）
Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This paper proposes a novel hybrid hierarchical deep learning model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small data set. A multi-layer RNN is equi…
Contrastive learning and supervised learning have both seen significant progress and success. However, thus far they have largely been treated as two separate objectives, brought together only by having a shared neural network. In this paper we show that through the perspective of hybrid discriminative-generative training of energy-based models we can make a direct connection between contrastive learning and supervised learning. Beyond presenting this unified view, we show our specific choice of approximation of the energy-based loss outperforms the existing practice in terms of classification…
In this paper, we propose a novel model for high-dimensional data, called the Hybrid Orthogonal Projection and Estimation (HOPE) model, which combines a linear orthogonal projection and a finite mixture model under a unified generative modeling framework. The HOPE model itself can be learned unsupervised from unlabelled data based on the maximum likelihood estimation as well as discriminatively from labelled data. More interestingly, we have shown the proposed HOPE models are closely related to neural networks (NNs) in a sense that each hidden layer can be reformulated as a HOPE model. As a re…
The linear primal-dual hybrid gradient (PDHG) method is a first-order method that splits convex optimization problems with saddle-point structure into smaller subproblems. Unlike those obtained in most splitting methods, these subproblems can generally be solved efficiently because they involve simple operations such as matrix-vector multiplications or proximal mappings that are fast to evaluate numerically. This advantage comes at the price that the linear PDHG method requires precise stepsize parameters for the problem at hand to achieve an optimal convergence rate. Unfortunately, these step…
USC Information Sciences Institute（南加州大学信息科学研究所）；Alexandria University（亚历山大大学）
Deep neural networks are powerful, massively parameterized machine learning models that have been shown to perform well in supervised learning tasks. However, very large amounts of labeled data are usually needed to train deep neural networks. Several semi-supervised learning approaches have been proposed to train neural networks using smaller amounts of labeled data with a large amount of unlabeled data. The performance of these semi-supervised methods significantly degrades as the size of labeled data decreases. We introduce Mutual-information-based Unsupervised & Semi-supervised Concurrent …
Institut National de Recherche en Informatique et en Automatique（法国国家信息与自动化研究所）；École Normale Supérieure（巴黎高等师范学院）；PSL Research University（巴黎文理研究大学）
Machine learning approached through supervised learning requires expensive annotation of data. This motivates weakly supervised learning, where data are annotated with incomplete yet discriminative information. In this paper, we focus on partial labelling, an instance of weak supervision where, from a given input, we are given a set of potential targets. We review a disambiguation principle to recover full supervision from weak supervision, and propose an empirical disambiguation algorithm. We prove exponential convergence rates of our algorithm under classical learnability assumptions, and we…
Facebook AI Research（脸书人工智能研究院）；Montréal Institute for Learning Algorithms (MILA), University of Montréal（蒙特利尔学习算法研究所（米拉），蒙特利尔大学）
We introduce the Neural Conditioner (NC), a self-supervised machine able to learn about all the conditional distributions of a random vector $X$. The NC is a function $NC(x \cdot a, a, r)$ that leverages adversarial training to match each conditional distribution $P(X_r|X_a=x_a)$. After training, the NC generalizes to sample from conditional distributions never seen, including the joint distribution. The NC is also able to auto-encode examples, providing data representations useful for downstream classification tasks. In sum, the NC integrates different self-supervised tasks (each being the es…
NeuroNet: A Novel Hybrid Self-Supervised Learning Framework for Sleep Stage Classification Using Single-Channel EEG
Korea University（高丽大学）；University of Cambridge（剑桥大学）；Stanford University School of Medicine（斯坦福大学医学院）；VA Palo Alto Health Care System（帕洛阿尔托退伍军人事务医疗系统）；Korea University College of Medicine（高丽大学医学院）
Toward Foundational Model for Sleep Analysis Using a Multimodal Hybrid Self-Supervised Learning Framework
Department of Brain and Cognitive Engineering, Korea University（脑科学与认知工程系，韩国大学）；Interdisciplinary Program in Precision Public Health, Korea University（精准公共卫生跨学科项目，韩国大学）；Department of Radiology, Stanford University School of Medicine（放射科，斯坦福大学医学院）；VA Palo Alto Health Care System（帕洛阿尔托医疗系统）；Department of Neurology, Korea University College of Medicine（神经病学系，韩国大学医学院）
This work aims to improve semi-supervised learning in a neural network architecture by introducing a hybrid supervised and unsupervised cost function. The unsupervised component is trained using a differentiable estimator of the Maximum Mean Discrepancy (MMD) distance between the network output and the target dataset. We introduce the notion of an $n$-channel network and several methods to improve performance of these nets based on supervised pre-initialization, and multi-scale kernels. This work investigates the effectiveness of these methods on language translation where very few quality tra…
Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）；Imperial College London（帝国理工学院）；Université de Lausanne（洛桑大学）；Logitech Europe S.A.（罗技欧洲公司）
Methods for extracting audio and speech features have been studied since pioneering work on spectrum analysis decades ago. Recent efforts are guided by the ambition to develop general-purpose audio representations. For example, deep neural networks can extract optimal embeddings if they are trained on large audio datasets. This work extends existing methods based on self-supervised learning by bootstrapping, proposes various encoder architectures, and explores the effects of using different pre-training datasets. Lastly, we present a novel training framework to come up with a hybrid audio repr…
