Related papers: Beyond Disagreement-based Agnostic Active Learning
Recently, Deep Neural Networks (DNNs) have made remarkable progress for text classification, which, however, still require a large number of labeled data. To train high-performing models with the minimal annotation cost, active learning is…
Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to greedily select the…
Active learning strategies respond to the costly labelling task in a supervised classification by selecting the most useful unlabelled examples in training a predictive model. Many conventional active learning algorithms focus on refining…
Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification model. For instance, uncertainty sampling depends on poorly…
In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in…
At its core, this thesis aims to enhance the practicality of deep learning by improving the label and training efficiency of deep learning models. To this end, we investigate data subset selection techniques, specifically active learning…
The goal of pool-based active learning is to judiciously select a fixed-sized subset of unlabeled samples from a pool to query an oracle for their labels, in order to maximize the accuracy of a supervised learner. However, the unsaid…
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically…
Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each…
Open intent detection is a significant problem in natural language understanding, which aims to identify the unseen open intent while ensuring known intent identification performance. However, current methods face two major challenges.…
Active learning is a learning strategy whereby the machine learning algorithm actively identifies and labels data points to optimize its learning. This strategy is particularly effective in domains where an abundance of unlabeled data…
Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is…
It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…
Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the…
Data generation and labeling are usually an expensive part of learning for robotics. While active learning methods are commonly used to tackle the former problem, preference-based learning is a concept that attempts to solve the latter by…
Deep learning based object detectors struggle generalizing to a new target domain bearing significant variations in object and background. Most current methods align domains by using image or instance-level adversarial feature alignment.…
We initiate the study of active learning algorithms for classifying strategic agents. Active learning is a well-established framework in machine learning in which the learner selectively queries labels, often achieving substantially higher…
Open intent classification is a challenging task in dialogue systems. On the one hand, it should ensure the quality of known intent identification. On the other hand, it needs to detect the open (unknown) intent without prior knowledge.…
Deep Neural Networks trained in a fully supervised fashion are the dominant technology in perception-based autonomous driving systems. While collecting large amounts of unlabeled data is already a major undertaking, only a subset of it can…
This work proposes a procedure for designing algorithms for specific adaptive data collection tasks like active learning and pure-exploration multi-armed bandits. Unlike the design of traditional adaptive algorithms that rely on…