UniSKGRep: A unified representation learning framework of social network and knowledge graph.

The human-oriented applications aim to exploit behaviors of people, which impose challenges on user modeling of integrating social network (SN) with knowledge graph (KG), and jointly analyzing two types of graph data. However, existing graph representation learning methods merely represent one of two graphs alone, and hence are unable to comprehensively consider features of both SN and KG with profiling the correlation between them, resulting in unsatisfied performance in downstream tasks. Considering the diverse gap of features and the difficulty of associating of the two graph data, we introduce a Unified Social Knowledge Graph Representation learning framework (UniSKGRep), with the goal to leverage the multi-view information inherent in the SN and KG for improving the downstream tasks of user modeling. To the best of our knowledge, we are the first to present a unified representation learning framework for SN and KG. Concretely, the SN and KG are organized as the Social Knowledge Graph (SKG), a unified representation of SN and KG. For the representation learning of SKG, first, two separate encoders in the Intra-graph model capture both the social-view and knowledge-view in two embedding spaces, respectively. Then the Inter-graph model is learned to associate the two separate spaces via bridging the semantics of overlapping node pairs. In addition, the overlapping node enhancement module is designed to effectively align two spaces with the consideration of a relatively small number of overlapping nodes. The two spaces are gradually unified by continuously iterating the joint training procedure. Extensive experiments on two real-world SKG datasets have proved the effectiveness of UniSKGRep in yielding general and substantial performance improvement compared with the strong baselines in various downstream tasks.

NEAWalk: Inferring missing social interactions via topological-temporal embeddings of social groups.

Real-world network data consisting of social interactions can be incomplete due to deliberately erased or unsuccessful data collection, which cause the misleading of social interaction analysis for many various time-aware applications. Naturally, the link prediction task has drawn much research interest to predict the missing edges in the incomplete social network. However, existing studies of link prediction cannot effectively capture the entangling topological and temporal dynamics already residing in the social network, thus cannot effectively reasoning the missing interactions in dynamic networks. In this paper, we propose the NEAWalk, a novel model to infer the missing social interaction based on topological-temporal features of patterns in the social group. NEAWalk samples the query-relevant walks containing both the historical and evolving information by focusing on the temporal constraint and designs a dual-view anonymization procedure for extracting both topological and temporal features from the collected walks to conduct the inference. Two-track experiments on several well-known network datasets demonstrate that the NEAWalk stably achieves superior performance against several state-of-the-art baseline methods.