To address the aforementioned limitations, we propose a novel social recommendation model named MCLA (Multi-relation Graph Contrastive Learning with an Adaptive Strategy). To maximize the use of rating data, we split the input data into multiple relations. The user–item rating data in the collabor...
Graph Contrastive Learning (GCL) with Graph Neural Networks (GNN) has emerged as a promising method for learning latent node representations in a self-supervised manner. Most of existing GCL methods employ random sampling for graph view augmentation and maximize the agreement of the node ...
Therefore, we propose a domain-aware model with multi-perspective, multi-positive contrastive learning. First, we adopt a self-supervised contrastive learning with multiple perspectives and multiple positive instances, which is capable of spacing the vectors of positive and negative instances from the ...
To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our strategy employs a multiscale perspective, enabling the extract...
Multi-label image classification with multi-layered multi-perspective dynamic semantic representation With the development of deep learning techniques, multi-label image classification tasks have achieved good performance. Recently, graph convolutional netw... W Kuang,Z Li - 《Machine Learning》 被引量:...
We perform video-paragraph contrastive learning to capture long-term temporal correlations from a fine-to-coarse perspective. Specifically, we first utilize the log-sum-exp operator on the frame-word similarity matrix to obtain fine-grained similarity between clip and caption. Additionally, we append...
2023Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation DegenerationSEMNeurIPS 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic PerspectiveSUMVCNeurIPS 2023Dual Label-Guided Graph Refnement for Multi-View Graph ClusteringDuaLGRAAAI ...
In the computer vision field, the view refers to an image displaying the same object sample (as shown in Fig.3) or part of it (as shown in Fig.5) from a specific perspective. The collection of images is the combination of different images (or views) that were captured from the same ...
However, we believed that (i) the visual feature extraction model by data augmentations and contrastive learning provides a solution to construct the association of spots between different samples; and (ii) the multi-view graph collaborative learning model can provide a novel perspective to integrate...
2.23 TCYB21 Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view(matlab) 2.24 TKDE20 Multi-View Spectral Clustering with High-Order Optimal Neighborhood Laplacian Matrix(matlab) 2.25 TKDE21 Consensus Graph Learning for Multi-view Clustering(matlab&python) ...