A Node-Collaboration-Informed Graph Convolutional Network for Precise Representation to Undirected Weighted Graphs

An undirected weighted graph (UWG) is frequently adopted to describe the interactions among a solo set of nodes from big data-connected applications like the user contact frequency from a social network services system. A graph convolutional network (GCN) is widely adopted to perform representation learning to a UWG for subsequent pattern analysis tasks such as clustering or missing data estimation. However, existing GCNs mostly neglects the latent collaborative information hidden in its connected node pairs. To address this issue, this study proposes to model the node collaborations via a symmetric latent factor analysis model, which is thus incorporated into a GCN model as a node-collaboration module for supplementing the collaboration loss. Based on this essential idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) model is proposed with three-fold ingredients: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module; b) Building the residual connection and weighted representation propagation to obtain high representation capacity; and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG. Empirical studies on four UWGs emerging from real applications demonstrate that owing to its efficient modeling of node-collaborations, the proposed NGCN significantly outperforms state-of-the-art GCNs in addressing the task of missing weight estimation. Meanwhile, its high scalability ensures its compatibility with more advanced GCN extensions, which will be further investigated in our future studies.