相关论文: When Less is Enough: Positive and Unlabeled Learni…

This paper explores the application of Positive-Unlabeled (PU) learning for enhanced Distributed Denial-of-Service (DDoS) detection in cloud environments. Utilizing the $\texttt{BCCC-cPacket-Cloud-DDoS-2024}$ dataset, we implement PU…

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning…

Semi-supervised learning (SSL) is a popular setting aiming to effectively utilize unlabelled data to improve model performance in downstream natural language processing (NLP) tasks. Currently, there are two popular approaches to make use of…

Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect…

We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes on specific test…

Conventional semi-supervised learning (SSL) ideally assumes that labeled and unlabeled data share an identical class distribution, however in practice, this assumption is easily violated, as unlabeled data often includes unknown class data,…

Existing algorithms aiming to learn a binary classifier from positive (P) and unlabeled (U) data generally require estimating the class prior or label noises ahead of building a classification model. However, the estimation and classifier…

In recent years, deep discriminative models have achieved extraordinary performance on supervised learning tasks, significantly outperforming their generative counterparts. However, their success relies on the presence of a large amount of…

Motivated by applications in protein function prediction, we consider a challenging supervised classification setting in which positive labels are scarce and there are no explicit negative labels. The learning algorithm must thus select…

Automatic speaker verification task has made great achievements using deep learning approaches with the large-scale manually annotated dataset. However, it's very difficult and expensive to collect a large amount of well-labeled data for…

Positive-unlabeled (PU) learning addresses binary classification when only a set of labeled positives is available alongside a pool of unlabeled samples drawn from a mixture of positives and negatives. Existing PU methods typically require…

Deep learning (DL) algorithms rely on massive amounts of labeled data. Semi-supervised learning (SSL) and active learning (AL) aim to reduce this label complexity by leveraging unlabeled data or carefully acquiring labels, respectively. In…

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Training of Convolutional Neural Networks (CNNs) with data with noisy labels is known to be a challenge. Based on the fact that directly providing the label to the data (Positive Learning; PL) has a risk of allowing CNNs to memorize the…

Semi-supervised learning (SSL) effectively leverages unlabeled data and has been proven successful across various fields. Current safe SSL methods believe that unseen classes in unlabeled data harm the performance of SSL models. However,…

Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we…

Log anomaly detection plays a critical role in ensuring the stability and reliability of software systems. However, existing approaches rely on large amounts of labeled log data, which poses significant challenges in real-world…

Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) like GPT-4 are trained on vast unlabelled code corpora, yet perform only marginally better…

Weakly supervised data are widespread and have attracted much attention. However, since label quality is often difficult to guarantee, sometimes the use of weakly supervised data will lead to unsatisfactory performance, i.e., performance…

Semi-supervised learning (SSL) methods assume that labeled data, unlabeled data and test data are from the same distribution. Open-set semi-supervised learning (Open-set SSL) considers a more practical scenario, where unlabeled data and…