Related papers: Reinforced Meta Active Learning

In supervised learning, we fit a single statistical model to a given data set, assuming that the data is associated with a singular task, which yields well-tuned models for specific use, but does not adapt well to new contexts. By contrast,…

Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models. However, in settings where personalization is necessary at deployment time to fine-tune the…

Meta-learning is a branch of machine learning which trains neural network models to synthesize a wide variety of data in order to rapidly solve new problems. In process control, many systems have similar and well-understood dynamics, which…

This paper introduces a novel approach to budgeted online active learning from finite-horizon data streams with extremely limited labeling budgets. In agricultural applications, such streams might include daily weather data over a growing…

We are interested in learning models of non-stationary environments, which can be framed as a multi-task learning problem. Model-free reinforcement learning algorithms can achieve good asymptotic performance in multi-task learning at a cost…

Active learning is a paradigm aimed at reducing the annotation effort by training the model on actively selected informative and/or representative samples. Another paradigm to reduce the annotation effort is self-training that learns from a…

Supervised machine learning often requires large training sets to train accurate models, yet obtaining large amounts of labeled data is not always feasible. Hence, it becomes crucial to explore active learning methods for reducing the size…

Active learning aims to efficiently build a labeled training set by strategically selecting samples to query labels from annotators. In this sequential process, each sample acquisition influences subsequent selections, causing dependencies…

We propose a general purpose active learning algorithm for structured prediction, gathering labeled data for training a model that outputs a set of related labels for an image or video. Active learning starts with a limited initial training…

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of…

Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…

In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it to train…

Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications. However, pretraining usually leverages predefined task sequences to learn general linguistic clues. The lack of…

Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively…

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries…

Co-training is a popular semi-supervised learning framework to utilize a large amount of unlabeled data in addition to a small labeled set. Co-training methods exploit predicted labels on the unlabeled data and select samples based on…

Active learning enables efficient model training by leveraging interactions between machine learning agents and human annotators. We study and propose a novel framework that formulates batch active learning from the sparse approximation's…

The non-stationary nature of data streams strongly challenges traditional machine learning techniques. Although some solutions have been proposed to extend traditional machine learning techniques for handling data streams, these approaches…

Active learning (AL) techniques optimally utilize a labeling budget by iteratively selecting instances that are most valuable for learning. However, they lack ``prerequisite checks'', i.e., there are no prescribed criteria to pick an AL…

Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by…