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

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 as gross corruption and missing values. Existing graph convolutions (GCs) generally focus on feature propagation on structured-graph which i) fail to address the graph data with missing values and ii) often perform susceptibility to large feature errors/noises. To address this issue, in this paper, we propose to incorporate robust norm feature learning mechanism into graph convolution and present Robust Norm Graph Convolutions (RNGCs) for graph data in the presence of feature noises and missing values. Our RNGCs are proposed based on the interpretation of GCs from a propagation function aspect of ‘data reconstruction on graph’. Based on it, we then derive our RNGCs by exploiting robust norm based propagation functions into GCs. Finally, we incorporate the derived RNGCs into an end-to-end network architecture and propose kinds of RNGCNs for graph data learning. Experimental results on several noisy datasets demonstrate the effectiveness and robustness of the proposed RNGCNs.