Shen Yinghan, Jiang Xuhui, Li Zijian, Wang Yuanzhuo, Xu Chengjin, Shen Huawei, Cheng Xueqi
Data Intelligent System Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China; School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China.
Data Intelligent System Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China; School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China.
Neural Netw. 2023 Jan;158:142-153. doi: 10.1016/j.neunet.2022.11.010. Epub 2022 Nov 14.
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.
以人为本的应用旨在利用人的行为，这对将社交网络（SN）与知识图谱（KG）集成的用户建模以及联合分析这两种图数据提出了挑战。然而，现有的图表示学习方法仅单独表示两种图中的一种，因此无法在剖析它们之间的相关性时全面考虑SN和KG的特征，导致在下游任务中的性能不尽人意。考虑到特征的多样差距以及两种图数据关联的困难，我们引入了一个统一的社交知识图谱表示学习框架（UniSKGRep），目标是利用SN和KG中固有的多视图信息来改善用户建模的下游任务。据我们所知，我们是第一个提出用于SN和KG的统一表示学习框架的。具体而言，SN和KG被组织成社交知识图谱（SKG），即SN和KG的统一表示。对于SKG的表示学习，首先，图内模型中的两个单独编码器分别在两个嵌入空间中捕获社交视图和知识视图。然后学习图间模型通过桥接重叠节点对的语义来关联这两个单独的空间。此外，重叠节点增强模块被设计用于在考虑相对较少数量的重叠节点的情况下有效地对齐两个空间。通过不断迭代联合训练过程，这两个空间逐渐统一。在两个真实世界的SKG数据集上进行的大量实验证明了UniSKGRep与各种下游任务中的强大基线相比，在产生总体和显著性能提升方面的有效性。
