COSTA: covariance-preserving feature augmentation for graph contrastive learning
Graph contrastive learning (GCL) improves graph representation learning, leading to SOTA
on various downstream tasks. The graph augmentation step is a vital but scarcely studied …
on various downstream tasks. The graph augmentation step is a vital but scarcely studied …
Spectral feature augmentation for graph contrastive learning and beyond
Although augmentations (eg, perturbation of graph edges, image crops) boost the efficiency
of Contrastive Learning (CL), feature level augmentation is another plausible …
of Contrastive Learning (CL), feature level augmentation is another plausible …
Mitigating the popularity bias of graph collaborative filtering: A dimensional collapse perspective
Abstract Graph-based Collaborative Filtering (GCF) is widely used in personalized
recommendation systems. However, GCF suffers from a fundamental problem where …
recommendation systems. However, GCF suffers from a fundamental problem where …
HRCF: Enhancing collaborative filtering via hyperbolic geometric regularization
In large-scale recommender systems, the user-item networks are generally scale-free or
expand exponentially. For the representation of the user and item, the latent features (aka …
expand exponentially. For the representation of the user and item, the latent features (aka …
Hicf: Hyperbolic informative collaborative filtering
Considering the prevalence of the power-law distribution in user-item networks, hyperbolic
space has attracted considerable attention and achieved impressive performance in the …
space has attracted considerable attention and achieved impressive performance in the …
Optimal block-wise asymmetric graph construction for graph-based semi-supervised learning
Graph-based semi-supervised learning (GSSL) serves as a powerful tool to model the
underlying manifold structures of samples in high-dimensional spaces. It involves two …
underlying manifold structures of samples in high-dimensional spaces. It involves two …
Contrastive cross-scale graph knowledge synergy
Graph representation learning via Contrastive Learning (GCL) has drawn considerable
attention recently. Efforts are mainly focused on gathering more global information via …
attention recently. Efforts are mainly focused on gathering more global information via …
A survey of multi-label classification based on supervised and semi-supervised learning
M Han, H Wu, Z Chen, M Li, X Zhang - International Journal of Machine …, 2023 - Springer
Multi-label classification algorithms based on supervised learning use all the labeled data to
train classifiers. However, in real life, many of the data are unlabeled, and it is costly to label …
train classifiers. However, in real life, many of the data are unlabeled, and it is costly to label …
Bipartite graph convolutional hashing for effective and efficient top-n search in hamming space
Searching on bipartite graphs is basal and versatile to many real-world Web applications,
eg, online recommendation, database retrieval, and query-document searching. Given a …
eg, online recommendation, database retrieval, and query-document searching. Given a …
Towards an optimal asymmetric graph structure for robust semi-supervised node classification
Graph Neural Networks (GNNs) have demonstrated great power for the semi-supervised
node classification task. However, most GNN methods are sensitive to the noise of graph …
node classification task. However, most GNN methods are sensitive to the noise of graph …