Temporal Knowledge Graph (TKG) is composed of a series of facts related to timestamps in the real world and has become the basis of many artificial intelligence applications. However, the existing TKG is usually incomplete. It has become a hot research task to infer missing facts based on existing facts in a TKG; namely, Temporal Knowledge Graph Completion (TKGC). The current mainstream TKGC models are embedded models that predict missing facts by representing entities, relations and timestamps as low-dimensional vectors. In order to deal with the TKG structure information, there are some models that try to introduce attention mechanism into the embedding process. But they only consider the structure information of entities or relations, and ignore the structure information of the whole TKG. Moreover, most of them usually treat timestamps as a general feature and cannot take advantage of the potential time series information of the timestamp. To solve these problems, wo propose a new Hierarchical Self-Attention Embedding (HSAE) model which inspired by self-attention mechanism and diachronic embedding technique. For structure information of the whole TKG, we divide the TKG into two layers: entity layer and relation layer, and then apply the self-attention mechanism to the entity layer and relation layer respectively to capture the structure information. For time series information of the timestamp, we capture them by combining positional encoding and diachronic embedding technique into the above two self-attention layers. Finally, we can get the embedded representation vectors of entities, relations and timestamps, which can be combined with other models for better results. We evaluate our model on three TKG datasets: ICEWS14, ICEWS05-15 and GDELT. Experimental results on the TKGC (interpolation) task demonstrate that our model achieves state-of-the-art results.

With the increasing popularity of Extensible Markup Language (XML) for data representation, there is a lot of interest in searching XML data. Due to the structural heterogeneity of XML, it is daunting for users to formulate exact queries and search for accurate answers. Especially when performing queries on fuzzy spatiotemporal data, the imprecision and uncertainty of information make the amount of query results is small or even empty. In this case, query relaxation is necessary. Existing efforts are mainly made on expanding simple queries. Once there are multiple conditions in the query, the existing algorithms often have poor performance. To address this problem, we first propose an adaptive query relaxation algorithm based on XML, which can handle complex queries efficiently. The approach does not depend on any specific domain or user, it can adaptively relax the initial query requirements, and classify the results into two sets after query relaxation. Moreover, the algorithm prestores the potential matching objects in the auxiliary structure, which provides support for efficient query. In addition, after query relaxation, we present the result sorting algorithm to address the problem of information overload. Finally, we report experimental results to show that our algorithms are superior to previous approaches.

Due to the widespread uses of uncertain spatiotemporal data, web ordinary users have access to query these data in various ways. However, users often cannot accurately give query constraints so that the query results may be empty or very few. Traditional algorithms cannot be used to deal with uncertain spatiotemporal data because they have no relaxation query on spatiotemporal attributes. Therefore, in this paper, the authors propose new flexible query algorithms, which add relaxation query processing for spatiotemporal attributes. Considering that XML has great advantages in exchanging and representing spatiotemporal data, they propose an uncertain spatiotemporal data model based on XML. According to the different number of relaxing attributes, they give SingleRelaxation algorithm and MultipleRelaxation algorithm. In addition, a T-List structure is designed to quickly locate the nodes' positions of uncertain spatiotemporal data, and RSort algorithm is proposed to sort accurate query results and extended query results. The experimental results show the superiority of the approach.

Temporal knowledge graphs (TKGs) have become useful resources for numerous Artificial Intelligence applications, but they are far from completeness. Inferring missing events in temporal knowledge graphs is a fundamental and challenging task. However, most existing methods solely focus on entity features or consider the entities and relations in a disjoint manner. They do not integrate the features of entities and relations in their modeling process. In this paper, we propose TPmod, a tendency-guided prediction model, to predict the missing events for TKGs (extrapolation). Differing from existing works, we propose two definitions for TKGs: the Goodness of relations and the Closeness of entity pairs. More importantly, inspired by the attention mechanism, we propose a novel tendency strategy to guide our aggregated process. It integrates the features of entities and relations, and assigns varying weights to different past events. What is more, we select the Gate Recurrent Unit (GRU) as our sequential encoder to model the temporal dependency in TKGs. Besides, the Softmax function is employed to generate the final decreasing group of candidate entities. We evaluate our model on two TKG datasets: GDELT-5 and ICEWS-250. Experimental results show that our method has a significant and consistent improvement compared to state-of-the-art baselines.