Related papers: Stream-based Active Learning with Verification Lat…

Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first generates samples online, which are then used to derive…

Active learning (AL) is a learning paradigm where an active learner has to train a model (e.g., a classifier) which is in principal trained in a supervised way, but in AL it has to be done by means of a data set with initially unlabeled…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

We study a robust alternative to empirical risk minimization called distributionally robust learning (DRL), in which one learns to perform against an adversary who can choose the data distribution from a specified set of distributions. We…

Digital data collected over the decades and data currently being produced with use of information technology is vastly the unlabeled data or data without description. The unlabeled data is relatively easy to acquire but expensive to label…

Temporal Action Localization (TAL) aims to predict both action category and temporal boundary of action instances in untrimmed videos, i.e., start and end time. Fully-supervised solutions are usually adopted in most existing works, and…

While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and…

Existing active learning (AL) strategies capture fundamentally different notions of data value, e.g., uncertainty or representativeness. Consequently, the effectiveness of strategies can vary substantially across datasets, models, and even…

This is the first work to investigate the effectiveness of BERT-based contextual embeddings in active learning (AL) tasks on cold-start scenarios, where traditional fine-tuning is infeasible due to the absence of labeled data. Our primary…

Concept drift detection is a crucial task in data stream evolving environments. Most of state of the art approaches designed to tackle this problem monitor the loss of predictive models. However, this approach falls short in many real-world…

Active Learning (AL) and Semi-supervised Learning are two techniques that have been studied to reduce the high cost of deep learning by using a small amount of labeled data and a large amount of unlabeled data. To improve the accuracy of…

Label concepts in multi-label data streams often experience drift in non-stationary environments, either independently or in relation to other labels. Transferring knowledge between related labels can accelerate adaptation, yet research on…

One important assumption underlying common classification models is the stationarity of the data. However, in real-world streaming applications, the data concept indicated by the joint distribution of feature and label is not stationary but…

Classifiers operating in a dynamic, real world environment, are vulnerable to adversarial activity, which causes the data distribution to change over time. These changes are traditionally referred to as concept drift, and several approaches…

In multi-domain learning (MDL) scenarios, high labeling effort is required due to the complexity of collecting data from various domains. Active Learning (AL) presents an encouraging solution to this issue by annotating a smaller number of…

Active learning (AL) is a machine learning algorithm that can achieve greater accuracy with fewer labeled training instances, for having the ability to ask oracles to label the most valuable unlabeled data chosen iteratively and…

Given a stream of entries over time in a multi-dimensional data setting where concept drift is present, how can we detect anomalous activities? Most of the existing unsupervised anomaly detection approaches seek to detect anomalous events…

Anomaly detection attempts at finding examples that deviate from the expected behaviour. Usually, anomaly detection is tackled from an unsupervised perspective because anomalous labels are rare and difficult to acquire. However, the lack of…

The standard supervised learning paradigm works effectively when training data shares the same distribution as the upcoming testing samples. However, this stationary assumption is often violated in real-world applications, especially when…

Many methods have been proposed to detect concept drift, i.e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms. However, the most of current detection methods…