Related papers: Multi-Pretext Attention Network for Few-shot Learn…

Attributed networks nowadays are ubiquitous in a myriad of high-impact applications, such as social network analysis, financial fraud detection, and drug discovery. As a central analytical task on attributed networks, node classification…

Despite the rapid advancement of unsupervised learning in visual representation, it requires training on large-scale datasets that demand costly data collection, and pose additional challenges due to concerns regarding data privacy.…

Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the…

Unsupervised feature selection is an important method to reduce dimensions of high dimensional data without labels, which is benefit to avoid ``curse of dimensionality'' and improve the performance of subsequent machine learning tasks, like…

When deep learning is applied to visual object recognition, data augmentation is often used to generate additional training data without extra labeling cost. It helps to reduce overfitting and increase the performance of the algorithm. In…

We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The…

Semi-supervised few-shot learning consists in training a classifier to adapt to new tasks with limited labeled data and a fixed quantity of unlabeled data. Many sophisticated methods have been developed to address the challenges this…

Learning to generate a task-aware base learner proves a promising direction to deal with few-shot learning (FSL) problem. Existing methods mainly focus on generating an embedding model utilized with a fixed metric (eg, cosine distance) for…

In recent years, heterogeneous graph few-shot learning has been proposed to address the label sparsity issue in heterogeneous graphs (HGs), which contain various types of nodes and edges. The existing methods have achieved good performance…

Recent work on few-shot learning \cite{tian2020rethinking} showed that quality of learned representations plays an important role in few-shot classification performance. On the other hand, the goal of self-supervised learning is to recover…

A major challenge in Natural Language Processing is obtaining annotated data for supervised learning. An option is the use of crowdsourcing platforms for data annotation. However, crowdsourcing introduces issues related to the annotator's…

Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. Most recent models have adopted a prototype-based paradigm for few-shot inference. These…

Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge.…

Deep neural networks (DNNs) that tackle the time series classification (TSC) task have provided a promising framework in signal processing. In real-world applications, as a data-driven model, DNNs are suffered from insufficient data.…

Existing few-shot learning (FSL) methods assume that there exist sufficient training samples from source classes for knowledge transfer to target classes with few training samples. However, this assumption is often invalid, especially when…

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent…

Graph few-shot learning has attracted increasing attention due to its ability to rapidly adapt models to new tasks with only limited labeled nodes. Despite the remarkable progress made by existing graph few-shot learning methods, several…

Real world data is mostly unlabeled or only few instances are labeled. Manually labeling data is a very expensive and daunting task. This calls for unsupervised learning techniques that are powerful enough to achieve comparable results as…

Meta-learning has become a practical approach towards few-shot image classification, where "a strategy to learn a classifier" is meta-learned on labeled base classes and can be applied to tasks with novel classes. We remove the requirement…

Graph classification aims to extract accurate information from graph-structured data for classification and is becoming more and more important in graph learning community. Although Graph Neural Networks (GNNs) have been successfully…