We observe that these audiovisual data naturally have temporal attributes, such as the time information for each frame in the video.
However, the uni-directional message-passing mechanism hinders such models from exploiting hidden mutual relations between entities in directed graphs.
To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space.
Graph neural networks (GNNs) have been widely investigated in the field of semi-supervised graph machine learning.
With the development of various applications, such as social networks and knowledge graphs, graph data has been ubiquitous in the real world.
To solve this issue, by extracting both temporal and structural information to learn more informative node representations, we propose a self-supervised method termed S2T for temporal graph learning.
Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views.
Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.
According to the graph types, existing KGR models can be roughly divided into three categories, i. e., static models, temporal models, and multi-modal models.
To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models.
Under multi-view scenarios, generating correct correspondences could be extremely difficult since anchors are not consistent in feature dimensions.
Deep graph clustering, which aims to reveal the underlying graph structure and divide the nodes into different clusters without human annotations, is a fundamental yet challenging task.
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations.
To address this issue, we propose a novel self-supervised deep graph clustering method termed Dual Correlation Reduction Network (DCRN) by reducing information correlation in a dual manner.
First, we entangle the attribute embedding and structure embedding by introducing a siamese network structure to share the parameters learned by both processes, which allows the network training to benefit from more abundant and diverse information.
In practice, since the label of the target domain is not available, we use the clustering information of the source domain to assign pseudo labels to the target domain samples, and then according to the source domain data prior knowledge guides those positive features to maximum the inter-class distance between different classes and mimimum the intra-class distance.
Multi-view clustering is an important yet challenging task in machine learning and data mining community.
Clustering is a fundamental task in the computer vision and machine learning community.
Specifically, in our network, an interdependency learning-based Structure and Attribute Information Fusion (SAIF) module is proposed to explicitly merge the representations learned by an autoencoder and a graph autoencoder for consensus representation learning.
The core components of CIFReNet are the Long-skip Refinement Module (LRM) and the Multi-scale Context Integration Module (MCIM).