Related papers: Instance exploitation for learning temporary conce…

In supervised learning, obtaining a large set of fully-labeled training data is expensive. We show that we do not always need full label information on every single training example to train a competent classifier. Specifically, inspired by…

Machine learning models are being increasingly used to automate decisions in almost every domain, and ensuring the performance of these models is crucial for ensuring high quality machine learning enabled services. Ensuring concept drift is…

In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes,…

Most state-of-the-art instance segmentation methods have to be trained on densely annotated images. While difficult in general, this requirement is especially daunting for biomedical images, where domain expertise is often required for…

The availability of abundant labeled data in recent years led the researchers to introduce a methodology called transfer learning, which utilizes existing data in situations where there are difficulties in collecting new annotated data.…

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored…

Given $k$ pre-trained classifiers and a stream of unlabeled data examples, how can we actively decide when to query a label so that we can distinguish the best model from the rest while making a small number of queries? Answering this…

We study the problem of learning in the presence of a drifting target concept. Specifically, we provide bounds on the error rate at a given time, given a learner with access to a history of independent samples labeled according to a target…

It has been found that stochastic algorithms often find good solutions much more rapidly than inherently-batch approaches. Indeed, a very useful rule of thumb is that often, when solving a machine learning problem, an iterative technique…

Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…

Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…

Noisy labels are both inevitable and problematic in machine learning methods, as they negatively impact models' generalization ability by causing overfitting. In the context of learning with noise, the transition matrix plays a crucial role…

Many real-world applications adopt multi-label data streams as the need for algorithms to deal with rapidly changing data increases. Changes in data distribution, also known as concept drift, cause the existing classification models to…

It is challenging but important to save annotation efforts in streaming data acquisition to maintain data quality for supervised learning base learners. We propose an ensemble active learning method to actively acquire samples for…

Active learning (AL) is a prominent technique for reducing the annotation effort required for training machine learning models. Deep learning offers a solution for several essential obstacles to deploying AL in practice but introduces many…

We consider the following basic learning task: given independent draws from an unknown distribution over a discrete support, output an approximation of the distribution that is as accurate as possible in $\ell_1$ distance (i.e. total…

A framework is introduced for actively and adaptively solving a sequence of machine learning problems, which are changing in bounded manner from one time step to the next. An algorithm is developed that actively queries the labels of the…

Labeling data for classification requires significant human effort. To reduce labeling cost, instead of labeling every instance, a group of instances (bag) is labeled by a single bag label. Computer algorithms are then used to infer the…

Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case,…

Data stream learning has been largely studied for extracting knowledge structures from continuous and rapid data records. In the semantic Web, data is interpreted in ontologies and its ordered sequence is represented as an ontology stream.…