In practical applications, there are often situations where data collection is hindered or incomplete. Graph convolutional networks (GCNs), which typically require complete and accurate data, encounter challenges when faced with missing or unavailable information. To address this issue, we propose an explicit technique called Partial Graph Convolution Networks (PaGCNs). This approach overcomes the limitation of GCNs on addressing the attribute-incomplete graph data.

Graph convolutional networks (GCNs) gain increasing attention on graph data learning tasks in recent years. However, in many applications, graph may come with an incomplete form where attributes of graph nodes are partially unknown/missing. Existing graph convolutions (GCs) are generally designed on complete graphs which cannot deal with attribute-incomplete graph data directly. To address this problem, in this article, we extend standard GC and develop an explicit Partial Graph Convolution (PaGC) for attribute-incomplete graph data. Our PaGC is derived based on the observation that the core neighborhood aggregator in GC operation can be equivalently viewed as an energy minimization model. Based on it, we can define a novel partial aggregation function and derive PaGC for incomplete graph data. Experiments demonstrate the effectiveness and efficiency of the proposed PaGCN.