Related papers: OLGA: One-cLass Graph Autoencoder

One-class classification (OCC) is a longstanding method for anomaly detection. With the powerful representation capability of the pre-trained backbone, OCC methods have witnessed significant performance improvements. Typically, most of…

We present a novel model called OCGAN for the classical problem of one-class novelty detection, where, given a set of examples from a particular class, the goal is to determine if a query example is from the same class. Our solution is…

Online continual learning (OCL) refers to the ability of a system to learn over time from a continuous stream of data without having to revisit previously encountered training samples. Learning continually in a single data pass is crucial…

One-class classification (OCC) algorithms aim to build classification models when the negative class is either absent, poorly sampled or not well defined. This unique situation constrains the learning of efficient classifiers by defining…

In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foster fair evaluation…

Graph contrastive learning (GCL), as a self-supervised learning method, can solve the problem of annotated data scarcity. It mines explicit features in unannotated graphs to generate favorable graph representations for downstream tasks.…

Multi-view learning has progressed rapidly in recent years. Although many previous studies assume that each instance appears in all views, it is common in real-world applications for instances to be missing from some views, resulting in…

Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The core of GCL is to maximise the mutual information between the…

One-shot learning has become an important research topic in the last decade with many real-world applications. The goal of one-shot learning is to classify unlabeled instances when there is only one labeled example per class. Conventional…

Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns. Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure.…

Anomalies are ubiquitous in all scientific fields and can express an unexpected event due to incomplete knowledge about the data distribution or an unknown process that suddenly comes into play and distorts observations. Due to such events'…

Graph contrastive learning (GCL) has emerged as an effective tool for learning unsupervised representations of graphs. The key idea is to maximize the agreement between two augmented views of each graph via data augmentation. Existing GCL…

In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come in an online…

Real-world heterogeneous graphs are inherently noisy and usually not in the optimal graph structures for downstream tasks, which often adversely affects the performance of GRL models in downstream tasks. Although Graph Structure Learning…

Object-centric learning (OCL) aims to learn structured scene representations that support compositional generalization and robustness to out-of-distribution (OOD) data. However, OCL models are often not evaluated regarding these goals.…

Graph Representation Learning (GRL) is an influential methodology, enabling a more profound understanding of graph-structured data and aiding graph clustering, a critical task across various domains. The recent incursion of attention…

Recent years, graph contrastive learning (GCL), which aims to learn representations from unlabeled graphs, has made great progress. However, the existing GCL methods mostly adopt human-designed graph augmentations, which are sensitive to…

Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either local or global…

Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classification, namely, learning a shared image feature to classify…

In this paper, we propose a novel subspace learning framework for one-class classification. The proposed framework presents the problem in the form of graph embedding. It includes the previously proposed subspace one-class techniques as its…