Related papers: Unsupervised Data Selection for Supervised Learnin…
Convolutional neural networks perform well on object recognition because of a number of recent advances: rectified linear units (ReLUs), data augmentation, dropout, and large labelled datasets. Unsupervised data has been proposed as another…
Representation learning with small labeled data have emerged in many problems, since the success of deep neural networks often relies on the availability of a huge amount of labeled data that is expensive to collect. To address it, many…
We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies…
Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…
Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…
Supervised Dictionary Learning has gained much interest in the recent decade and has shown significant performance improvements in image classification. However, in general, supervised learning needs a large number of labelled samples per…
Finding valuable training data points for deep neural networks has been a core research challenge with many applications. In recent years, various techniques for calculating the "value" of individual training datapoints have been proposed…
Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component,…
Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…
Deep neural networks have been widely used in communication signal recognition and achieved remarkable performance, but this superiority typically depends on using massive examples for supervised learning, whereas training a deep neural…
Latent representations are critical for the performance and robustness of machine learning models, as they encode the essential features of data in a compact and informative manner. However, in vision tasks, these representations are often…
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…
Time series anomaly detection presents various challenges due to the sequential and dynamic nature of time-dependent data. Traditional unsupervised methods frequently encounter difficulties in generalization, often overfitting to known…
The paradigm of data programming, which uses weak supervision in the form of rules/labelling functions, and semi-supervised learning, which augments small amounts of labelled data with a large unlabelled dataset, have shown great promise in…
Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as probabilistic models…
Universal supervised learning is considered from an information theoretic point of view following the universal prediction approach, see Merhav and Feder (1998). We consider the standard supervised "batch" learning where prediction is done…
Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…
Semi-supervised learning (SSL) is a class of supervised learning tasks and techniques that also exploits the unlabeled data for training. SSL significantly reduces labeling related costs and is able to handle large data sets. The primary…
The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On the other hand, Machine Translation Systems are mostly…
The real challenge in pattern recognition task and machine learning process is to train a discriminator using labeled data and use it to distinguish between future data as accurate as possible. However, most of the problems in the real…