The node classification task is one where the algorithm has to determine the labelling of samples (represented as nodes) by looking at the labels of their neighbours.
( Image credit: Fast Graph Representation Learning With PyTorch Geometric )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
As GNNs operate on non-Euclidean data, their irregular data access patterns cause considerable computational costs and overhead on conventional architectures, such as GPU and CPU.
Based on nodes' geometrical relationships in the latent space, WGCN differentiates latent, in-, and out-neighbors with an attention-based geometrical aggregation.
In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.
In this paper, we introduce a novel Local and Global Disentangled Graph Convolutional Network (LGD-GCN) to capture both local and global information for graph disentanglement.
Recent works have sought to address this problem using a two-stage approach, which first aggregates data along graph edges, then trains a classifier without using additional graph information.
Specifically, we developed a manifold-preserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation.
In this paper, we propose a deep attributed network representation learning via attribute enhanced neighborhood (DANRL-ANE) model to improve the robustness and effectiveness of node representations.
Backdoor attacks represent a serious threat to neural network models.