Related papers: Does Deep Active Learning Work in the Wild?
While deep learning succeeds in a wide range of tasks, it highly depends on the massive collection of annotated data which is expensive and time-consuming. To lower the cost of data annotation, active learning has been proposed to…
Automated machine learning (AutoML) and deep learning (DL) are two cutting-edge paradigms used to solve a myriad of inductive learning tasks. In spite of their successes, little guidance exists for when to choose one approach over the other…
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…
Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box…
Active learning (AL) aims at reducing labeling effort by identifying the most valuable unlabeled data points from a large pool. Traditional AL frameworks have two limitations: First, they perform data selection in a multi-round manner,…
Automated detection of software vulnerabilities is a fundamental problem in software security. Existing program analysis techniques either suffer from high false positives or false negatives. Recent progress in Deep Learning (DL) has…
The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types such as images and…
Most of the existing learning models, particularly deep neural networks, are reliant on large datasets whose hand-labeling is expensive and time demanding. A current trend is to make the learning of these models frugal and less dependent on…
The advent of large language models (LLMs) capable of producing general-purpose representations lets us revisit the practicality of deep active learning (AL): By leveraging frozen LLM embeddings, we can mitigate the computational costs of…
Deep Reinforcement Learning (RL) algorithms can solve complex sequential decision tasks successfully. However, they have a major drawback of having poor sample efficiency which can often be tackled by knowledge reuse. In Multi-Agent…
Labeling data is one of the most costly processes in machine learning pipelines. Active learning is a standard approach to alleviating this problem. Pool-based active learning first builds a pool of unlabelled data and iteratively selects…
Deep Reinforcement Learning (DRL) is a paradigm of artificial intelligence where an agent uses a neural network to learn which actions to take in a given environment. DRL has recently gained traction from being able to solve complex…
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 address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced…
Digital systems find it challenging to keep up with cybersecurity threats. The daily emergence of more than 560,000 new malware strains poses significant hazards to the digital ecosystem. The traditional malware detection methods fail to…
During recent years, active learning has evolved into a popular paradigm for utilizing user's feedback to improve accuracy of learning algorithms. Active learning works by selecting the most informative sample among unlabeled data and…
Although Reinforcement Learning (RL) has shown to be capable of producing impressive results, its use is limited by the impact of its hyperparameters on performance. This often makes it difficult to achieve good results in practice.…
Deep-learning-based models are increasingly used to emulate scientific simulations to accelerate scientific research. However, accurate, supervised deep learning models require huge amount of labelled data, and that often becomes the…
Efficient exploration is one of the key challenges for reinforcement learning (RL) algorithms. Most traditional sample efficiency bounds require strategic exploration. Recently many deep RL algorithms with simple heuristic exploration…
Active learning (AL) selects the most beneficial unlabeled samples to label, and hence a better machine learning model can be trained from the same number of labeled samples. Most existing active learning for regression (ALR) approaches are…