Related papers: Partial-label Learning with Mixed Closed-set and O…
This thesis makes considerable contributions to the realm of machine learning, specifically in the context of open-world scenarios where systems face previously unseen data and contexts. Traditional machine learning models are usually…
Multi-instance partial-label learning (MIPL) is a weakly supervised framework that extends the principles of multi-instance learning (MIL) and partial-label learning (PLL) to address the challenges of inexact supervision in both instance…
Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…
Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requires a large amount of labeled data for training, which is…
In contrast to conventional (single-label) classification, the setting of multilabel classification (MLC) allows an instance to belong to several classes simultaneously. Thus, instead of selecting a single class label, predictions take the…
In supervised machine learning, the assumption that training data is labelled correctly is not always satisfied. In this paper, we investigate an instance of labelling error for classification tasks in which the dataset is corrupted with…
Partial-Label Learning (PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error…
Partial Multi-label Learning (PML) aims to induce the multi-label predictor from datasets with noisy supervision, where each training instance is associated with several candidate labels but only partially valid. To address the noisy issue,…
Partial label learning is a prominent weakly supervised classification task, where each training instance is ambiguously labeled with a set of candidate labels. In real-world scenarios, candidate labels are often influenced by instance…
The goal of multi-label learning (MLL) is to associate a given instance with its relevant labels from a set of concepts. Previous works of MLL mainly focused on the setting where the concept set is assumed to be fixed, while many real-world…
Complementary Labels Learning (CLL) arises in many real-world tasks such as private questions classification and online learning, which aims to alleviate the annotation cost compared with standard supervised learning. Unfortunately, most…
Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning…
Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates which can be false positive or similar to the ground-truth label. In this paper, we…
Pool-based Active Learning (AL) has achieved great success in minimizing labeling cost by sequentially selecting informative unlabeled samples from a large unlabeled data pool and querying their labels from oracle/annotators. However,…
Open-set Semi-supervised Learning (OSSL) holds a realistic setting that unlabeled data may come from classes unseen in the labeled set, i.e., out-of-distribution (OOD) data, which could cause performance degradation in conventional SSL…
New intent discovery is a crucial capability for task-oriented dialogue systems. Existing methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data through pre-training and clustering stages. They either…
Partial multi-label learning and complementary multi-label learning are two popular weakly supervised multi-label classification paradigms that aim to alleviate the high annotation costs of collecting precisely annotated multi-label data.…
PU learning refers to the classification problem in which only part of positive samples are labeled. Existing PU learning methods treat unlabeled samples equally. However, in many real tasks, from common sense or domain knowledge, some…
Diminishing the impact of false-positive labels is critical for conducting disambiguation in partial label learning. However, the existing disambiguation strategies mainly focus on exploiting the characteristics of individual partial label…