GmCN: Graph Mask Convolutional Network
This work addresses graph learning robustness for applications like social networks or bioinformatics, but it is incremental as it builds on existing GCN frameworks.
The paper tackles the problem of fixed neighborhood aggregation in Graph Convolutional Networks (GCNs), which can be suboptimal and sensitive to graph noise, by proposing GmCN, a method that allows nodes to adaptively select optimal neighbors for feature aggregation, with experiments validating its effectiveness.
Graph Convolutional Networks (GCNs) have shown very powerful for graph data representation and learning tasks. Existing GCNs usually conduct feature aggregation on a fixed neighborhood graph in which each node computes its representation by aggregating the feature representations of all its neighbors which is biased by its own representation. However, this fixed aggregation strategy is not guaranteed to be optimal for GCN based graph learning and also can be affected by some graph structure noises, such as incorrect or undesired edge connections. To address these issues, we propose a novel Graph mask Convolutional Network (GmCN) in which nodes can adaptively select the optimal neighbors in their feature aggregation to better serve GCN learning. GmCN can be theoretically interpreted by a regularization framework, based on which we derive a simple update algorithm to determine the optimal mask adaptively in GmCN training process. Experiments on several datasets validate the effectiveness of GmCN.