Inductive knowledge graph embedding (KGE) aims to embed unseen entities in emerging knowledge graphs (KGs). The major recent studies of inductive KGE embed unseen entities by aggregating information from their neighboring entities and relations with graph neural networks (GNNs). However, these methods rely on the existing neighbors of unseen entities and suffer from two common problems: data sparsity and feature smoothing. Firstly, the data sparsity problem means unseen entities usually emerge with few triplets containing insufficient information. Secondly, the effectiveness of the features extracted from original KGs will degrade when repeatedly propagating these features to represent unseen entities in emerging KGs, which is termed feature smoothing problem. To tackle the two problems, we propose a novel model entitled Meta-Learning Based Memory Graph Convolutional Network (MMGCN) consisting of three different components: 1) the two-layer information transforming module (TITM) developed to effectively transform information from original KGs to emerging KGs; 2) the hyper-relation feature initializing module (HFIM) proposed to extract type-level features shared between KGs and obtain a coarse-grained representation for each entity with these features; and 3) the meta-learning training module (MTM) designed to simulate the few-shot emerging KGs and train the model in a meta-learning framework. The extensive experiments conducted on the few-shot link prediction task for emerging KGs demonstrate the superiority of our proposed model MMGCN compared with state-of-the-art methods.

Author name disambiguation (AND) is a central task in academic search, which has received more attention recently accompanied by the increase of authors and academic publications. To tackle the AND problem, existing studies have proposed various approaches based on different types of information, such as raw document features (e.g., co-authors, titles, and keywords), the fusion feature (e.g., a hybrid publication embedding based on multiple raw document features), the local structural information (e.g., a publication's neighborhood information on a graph), and the global structural information (e.g., interactive information between a node and others on a graph). However, there has been no work taking all the above-mentioned information into account and taking full advantage of the contributions of each raw document feature for the AND problem so far. To fill the gap, we propose a novel framework named EAND (Towards Effective Author Name Disambiguation by Hybrid Attention). Specifically, we design a novel feature extraction model, which consists of three hybrid attention mechanism layers, to extract key information from the global structural information and the local structural information that are generated from six similarity graphs constructed based on different similarity coefficients, raw document features, and the fusion feature. Each hybrid attention mechanism layer contains three key modules: a local structural perception, a global structural perception, and a feature extractor. Additionally, the mean absolute error function in the joint loss function is used to introduce the structural information loss of the vector space. Experimental results on two real-world datasets demonstrate that EAND achieves superior performance, outperforming state-of-the-art methods by at least +2.74% in terms of the micro-F1 score and +3.31% in terms of the macro-F1 score.

Linking user accounts belonging to the same user across different platforms with location data has received significant attention, due to the popularization of GPS-enabled devices and the wide range of applications benefiting from user account linkage (e.g., cross-platform user profiling and recommendation). Different from most existing studies which only focus on user account linkage across two platforms, we propose a novel model ULMP (i.e., user account linkage across multiple platforms), with the goal of effectively and efficiently linking user accounts across multiple platforms with location data. Despite of the practical significance brought by successful user linkage across multiple platforms, this task is very challenging compared with the ones across two platforms. The major challenge lies in the fact that the number of user combinations shows an explosive growth with the increase of the number of platforms. To tackle the problem, a novel method GTkNN is first proposed to prune the search space by efficiently retrieving top-k candidate user accounts indexed with well-designed spatial and temporal index structures. Then, in the pruned space, a match score based on kernel density estimation combining both spatial and temporal information is designed to retrieve the linked user accounts. The extensive experiments conducted on four real-world datasets demonstrate the superiority of the proposed model ULMP in terms of both effectiveness and efficiency compared with the state-of-art methods.