Related papers: Convergence Behavior of an Adversarial Weak Superv…
Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can…
Semisupervised methods are techniques for using labeled data $(X_1,Y_1),\ldots,(X_n,Y_n)$ together with unlabeled data $X_{n+1},\ldots,X_N$ to make predictions. These methods invoke some assumptions that link the marginal distribution $P_X$…
Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…
Decentralized machine learning often relies on outsourcing computations, such as gradient evaluations, to untrusted worker nodes. Existing robust aggregation methods can mitigate malicious behavior under honest-majority assumptions, but may…
The goal in semi-supervised learning is to effectively combine labeled and unlabeled data. One way to do this is by encouraging smoothness across edges in a graph whose nodes correspond to input examples. In many graph-based methods, labels…
Transductive graph-based semi-supervised learning methods usually build an undirected graph utilizing both labeled and unlabeled samples as vertices. Those methods propagate label information of labeled samples to neighbors through their…
Overconfidence is a common issue for deep neural networks, limiting their deployment in real-world applications. To better estimate confidence, existing methods mostly focus on fully-supervised scenarios and rely on training labels. In this…
Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to…
We argue that a form of the valuable information provided by the auxiliary information is its implied data clustering information. For instance, considering hashtags as auxiliary information, we can hypothesize that an Instagram image will…
Distributed representations of words which map each word to a continuous vector have proven useful in capturing important linguistic information not only in a single language but also across different languages. Current unsupervised…
Neural network compression has recently received much attention due to the computational requirements of modern deep models. In this work, our objective is to transfer knowledge from a deep and accurate model to a smaller one. Our…
We study the problem of learning an adversarially robust predictor to test time attacks in the semi-supervised PAC model. We address the question of how many labeled and unlabeled examples are required to ensure learning. We show that…
Recently, researches related to unsupervised disentanglement learning with deep generative models have gained substantial popularity. However, without introducing supervision, there is no guarantee that the factors of interest can be…
In recent years, semi-supervised learning (SSL) has shown tremendous success in leveraging unlabeled data to improve the performance of deep learning models, which significantly reduces the demand for large amounts of labeled data. Many SSL…
Adversarial attacks exploit the vulnerabilities of convolutional neural networks by introducing imperceptible perturbations that lead to misclassifications, exposing weaknesses in feature representations and decision boundaries. This paper…
In semi-supervised learning for classification, it is assumed that every ground truth class of data is present in the small labelled dataset. Many real-world sparsely-labelled datasets are plausibly not of this type. It could easily be the…
Learning transferable data representations from abundant unlabeled data remains a central challenge in machine learning. Although numerous self-supervised learning methods have been proposed to address this challenge, a significant class of…
Self-training is a classical approach in semi-supervised learning which is successfully applied to a variety of machine learning problems. Self-training algorithm generates pseudo-labels for the unlabeled examples and progressively refines…
Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…
Deep Learning (DL) based methods for object detection achieve remarkable performance at the cost of computationally expensive training and extensive data labeling. Robots embodiment can be exploited to mitigate this burden by acquiring…