Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited. Although it is often established that the average accuracy for the entire population of data is improved, it is unclear how SSL fares with different sub-populations. Understanding the above question has substantial fairness implications when these different sub-populations are defined by the demographic groups we aim to treat fairly. In this paper, we reveal the disparate impacts of deploying SSL: the sub-population who has a higher baseline accuracy without using SSL (the ``rich" sub-population) tends to benefit more from SSL; while the sub-population who suffers from a low baseline accuracy (the ``poor" sub-population) might even observe a performance drop after adding the SSL module. We theoretically and empirically establish the above observation for a broad family of SSL algorithms, which either explicitly or implicitly use an auxiliary ``pseudo-label". Our experiments on a set of image and text classification tasks confirm our claims. We discuss how this disparate impact can be mitigated and hope that our paper will alarm the potential pitfall of using SSL and encourage a multifaceted evaluation of future SSL algorithms. Code is available at github.com/UCSC-REAL/Disparate-SSL.

We propose a novel framework to conduct field extraction from forms with unlabeled data. To bootstrap the training process, we develop a rule-based method for mining noisy pseudo-labels from unlabeled forms. Using the supervisory signal from the pseudo-labels, we extract a discriminative token representation from a transformer-based model by modeling the interaction between text in the form. To prevent the model from overfitting to label noise, we introduce a refinement module based on a progressive pseudo-label ensemble. Experimental results demonstrate the effectiveness of our framework.

GANs is one of the helpful techniques from Machine Learning related to photo editing. A Generative Adversarial Network also known as -- GAN is a group of Machine Learning. It was designed by Ian Goodfellow and his colleagues in 2014. Initially, they were put forward as a generative model for unsupervised learning but they are being extremely useful for semisupervised learning, supervised learning, and also for reinforcement learning. They are created with the help of two neural networks that compete with each other and have the ability to create new output by analyzing, capturing, and copying the variation from the given datasets.

Learning from data sequentially arriving, possibly in a non i.i.d. way, with changing task distribution over time is called continual learning. Much of the work thus far in continual learning focuses on supervised learning and some recent works on unsupervised learning. In many domains, each task contains a mix of labelled (typically very few) and unlabelled (typically plenty) training examples, which necessitates a semi-supervised learning approach. To address this in a continual learning setting, we propose a framework for semi-supervised continual learning called Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL). Our framework has a hypernetwork that learns the meta-distribution that generates the weights of a semi-supervised auxiliary classifier generative adversarial network $(\textit{Semi-ACGAN})$ as the base network. We consolidate the knowledge of sequential tasks in the hypernetwork, and the base network learns the semi-supervised learning task. Further, we present $\textit{Semi-Split CIFAR-10}$, a new benchmark for continual semi-supervised learning, obtained by modifying the $\textit{Split CIFAR-10}$ dataset, in which the tasks with labelled and unlabelled data arrive sequentially. Our proposed model yields significant improvements in the continual semi-supervised learning setting. We compare the performance of several existing continual learning approaches on the proposed continual semi-supervised learning benchmark of the Semi-Split CIFAR-10 dataset.

Most of the time people start their machine learning journey with few basic techniques in which Unsupervised Learning, Supervised Learning, and Reinforcement Learning is the major ones. For any effective business operations, good use of information plays a vital role. However, at some point, the information goes beyond simple processing capacity. For that matter, machine learning plays its part. Before anything happens, information needs to be explored and certain processing needs to be done on it.

We look into Generative Adversarial Network (GAN), its prevalent variants and applications in a number of sectors. GANs combine two neural networks that compete against one another using zero-sum game theory, allowing them to create much crisper and discrete outputs. GANs can be used to perform image processing, video generation and prediction, among other computer vision applications. GANs can also be utilised for a variety of science-related activities, including protein engineering, astronomical data processing, remote sensing image dehazing, and crystal structure synthesis. Other notable fields where GANs have made gains include finance, marketing, fashion design, sports, and music. Therefore in this article we provide a comprehensive overview of the applications of GANs in a wide variety of disciplines. We first cover the theory supporting GAN, GAN variants, and the metrics to evaluate GANs. Then we present how GAN and its variants can be applied in twelve domains, ranging from STEM fields, such as astronomy and biology, to business fields, such as marketing and finance, and to arts, such as music. As a result, researchers from other fields may grasp how GANs work and apply them to their own study. To the best of our knowledge, this article provides the most comprehensive survey of GAN's applications in different fields.

Semi-supervised learning is a machine learning technique of deriving useful information from both labelled and unlabelled data. Before doing this tutorial, you should have basic familiarity with supervised learning on images with PyTorch. We will omit reinforcement learning here and concentrate on the first two types. In supervised learning, our data consists of labelled objects. A machine learning model is tasked with learning how to assign labels (or values) to objects.

Machine Learning (ML) has bought significant promises in different fields in both academia and industry. Day by day, ML has grown its engagement in a comprehensive list of applications such as image, speech recognition, pattern recognition, optimization, natural language processing, and recommendations, and so many others. Programming computers to learn from experience should eventually eliminate the need for much of this detailed programming effort. Machine Learning can be divided into four main techniques: regression, classification, clustering, and reinforcement learning. Those techniques solve problems with different natures in mainly two forms: supervised and unsupervised learning.

Machine Learning can be defined as an approach to achieve artificial intelligence through systems or software models that can learn from experience to find patterns in a set of data. Google uses artificial intelligence and machine learning in almost all of its applications. Google Photos display photos related to your search terms and animate similar photos from your albums into quick videos. Gmail suggest phrases and complete sentences in emails. Google Assistant can take over real-world tasks such as booking a haircut appointment over phone.

Raven's Progressive Matrices (RPM) is highly correlated with human intelligence, and it has been widely used to measure the abstract reasoning ability of humans. In this paper, to study the abstract reasoning capability of deep neural networks, we propose the first unsupervised learning method for solving RPM problems. Since the ground truth labels are not allowed, we design a pseudo target based on the prior constraints of the RPM formulation to approximate the ground truth label, which effectively converts the unsupervised learning strategy into a supervised one. However, the correct answer is wrongly labelled by the pseudo target, and thus the noisy contrast will lead to inaccurate model training. To alleviate this issue, we propose to improve the model performance with negative answers. Moreover, we develop a decentralization method to adapt the feature representation to different RPM problems. Extensive experiments on three datasets demonstrate that our method even outperforms some of the supervised approaches. Our code is available at https://github.com/visiontao/ncd.