AlphaGalileo

Adapting to the Stream: An Instance-Attention GNN Method for Irregular Multivariate Time ...

DynIMTS replaces static graphs with instance-attention that updates edge weights on the fly, delivering SOTA imputation and P12 classification ...
GitHub

Trajectory–User Linking via Heterogeneous Preference Graph and Dual-Encoder Mutual ...

(1) Duration (Days): This represents the total time span of the dataset, calculated as the number of days between the first and the last check-in recorded in the entire dataset. For instance, the ...
IEEE

MBGCN: Multi-view Block-wise Graph Convolutional Networks on Large-scale Graphs

Abstract: Existing methods based on graph convolutional network often struggle with large-scale graphs due to their high computing consumption and inefficiency. Although strategies such as edge ...
Microsoft

Refined graph encoder embedding via self-training and latent community recovery

This paper introduces a refined graph encoder embedding method, enhancing the original graph encoder embedding through linear transformation, self-training, and hidden community recovery within ...
IEEE

RNGCNs: Robust Norm Graph Convolutional Networks in the Presence of Missing Data and Large ...

Abstract: Graph Convolutional Networks (GCNs) have been widely studied for attribute graph data learning. In many applications, graph node attributes/features may contain various kinds of noises, such ...