DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion

Recently, large-scale knowledge graphs (KGs) have become a key asset for search, analytics, recommendations and data integration. Large-scale KGs provide millions of facts about the real world. Each fact is composed as (subject, relation, object), e.g., the triplet (“Cristiano Ronaldo”, playFor, “Real Madrid”). However, these facts are blind to the temporal dimension. Actually, knowledge in practice is time-variant and many relations are only valid for a certain period of time. This phenomenon highlights the importance of building temporal knowledge graphs. In particular, knowledge in temporal KG is represented as (subject, relation, object, valid time), e.g., (“Cristiano Ronaldo”, playFor, “Real Madrid”, “[2009, 2018]”. However, research on temporal KG is very current and there are still many problems needed to be addressed. One obvious problem is that the size of temporal KG is still very small. For example, only 6.6% of the facts are time-aware in one of the largest knowledge graphs, YAGO3. In addition, 71% of people have no known place of birth, and 75% have no known nationality in Freebase. Furthermore, over 87.7% of the facts are uncovered in Japanese DBpedia compared with English DBpedia. Therefore, in this thesis, we study how to enlarge and enrich temporal knowledge graphs from three aspects, namely, temporal KG enrichment. In particular, we study the enrichment problem from the following aspects: (1) volume, (2) completeness, and (3) coverage.Our first solution is temporal knowledge harvesting which extracts temporal knowledge from free text directly. However, text corpus is noisy, and extracting structured temporal facts with high accuracy and coverage is very challenging. Inspired by pattern-based systems, we propose a temporal knowledge harvesting framework. In particular, we propose various techniques to extract temporal patterns, including corpus annotation, pattern generation, scoring and clustering. These techniques can reduce ambiguity in the text corpus and can improve both the accuracy and coverage of the extracted patterns. Second, we leverage the extracted patterns to harvest temporal knowledge. To improve the accuracy, we propose a parse-tree-based method. And to increase the coverage, we consider the relationships between tree components, including part of speech (POS), clause types, constituency and dependency. Experiments on real-world datasets verify the effectiveness of our proposed framework.Our second solution is temporal knowledge graph completion. Temporal KG completion is the task of inferring unobserved edges between entity pairs. Generally, temporal KG completion relies on the temporal KG embeddings technique, which learns the low-dimensional representations of all KG components. As research on temporal KG embedding is very current, we study both the embedding and the completion problems. In particular, we observe that contexts are extremely useful for learning the representations of entities and for inferring the unknown time intervals. As a result, we propose a context-aware embedding model for KG embeddings and a context-based temporal inference model for KG completion. In our embedding model, we not only capture factual plausibility as traditional methods did, but also propose a new measure on contexts, named temporal consistency. It measures how well the target entity interacts with its surrounding contexts on the temporal dimension. Our completion model is based on the embedding model, and further captures the interactions on the entity dimension. Extensive experiments verify the effectiveness of our models.Our third solution is temporal knowledge graph alignment which aims to discover the SameAs edges across two temporal KGs. Not like previous attribute-based alignment models, we further divide attribute facts into character facts, digit facts and time facts. In particular, we observe that the context information is extremely useful for the identification of the same entities. Therefore, we propose an alignment model on leveraging temporal contexts to represent entities. However, contexts of the same object can be very different. For example, the value of career predicate changed from “football player” to “coach” for the football player “Zidane”. This is because entities are evolving over time and thus the predicate values can be different. In our framework, we propose an alignment module that simulates the entity evolving process. Specifically, this module captures the interactions between contexts and aggregates context information to represent the entity. Lastly, we found that not all contexts are relevant, e.g., height v.s. career. Actually, only the relevant contexts are useful for capturing the evolving. Therefore, we propose a clustering approach for grouping relevant contexts together. Our experimental results validate the superiority of our proposed alignment model.

One of the key requirements to facilitate the semantic analytics of information regarding contemporary and historical events on the Web, in the news and in social media is the availability of reference knowledge repositories containing comprehensive representations of events, entities and temporal relations. Existing knowledge graphs, with popular examples including DBpedia, YAGO and Wikidata, focus mostly on entity-centric information and are insufficient in terms of their coverage and completeness with respect to events and temporal relations. In this article we address this limitation, formalise the concept of a temporal knowledge graph and present its instantiation - EventKG. EventKG is a multilingual event-centric temporal knowledge graph that incorporates over 690 thousand events and over 2.3 million temporal relations obtained from several large-scale knowledge graphs and semi-structured sources and makes them available through a canonical RDF representation. Whereas popular entities often possess hundreds of relations within a temporal knowledge graph such as EventKG, generating a concise overview of the most important temporal relations for a given entity is a challenging task. In this article we demonstrate an application of EventKG to biographical timeline generation, where we adopt a distant supervision method to identify relations most relevant for an entity biography. Our evaluation results provide insights on the characteristics of EventKG and demonstrate the effectiveness of the proposed biographical timeline generation method.

Representation learning for temporal knowledge graphs has attracted increasing attention in recent years. In this paper, we study the problem of learning dynamic embeddings for temporal knowledge graphs. We address this problem by proposing a Dynamic Bayesian Knowledge Graphs Embedding model (DBKGE), which is able to dynamically track the semantic representations of entities over time in a joint metric space and make predictions for the future. Unlike other temporal knowledge graph embedding methods, DBKGE is a novel probabilistic representation learning method that aims at inferring dynamic embeddings of entities in a streaming scenario. To obtain high-quality embeddings and model their uncertainty, our DBKGE embeds entities with means and variances of Gaussian distributions. Based on amortized inference, an online inference algorithm is proposed to jointly learn the latent representations of entities and smooth their changes across time. Experiments on Yago and Wiki datasets demonstrate that our proposed algorithm outperforms the state-of-the-art static and temporal knowledge graph embedding models.

Temporal knowledge graphs (TKGs) have been widely used in various fields, and predicting missing knowledge graph inference has been widely explored. However, the task of reasoning about potential future facts on TKGs is more challenging and has attracted the attention of researchers. As the unknowability of future events complicates inference, a thorough study of the characteristics of historical facts becomes crucial. The study of the concurrency of historical events and the underlying common patterns of relation-ships facilitates reasoning about future facts. In this paper, we propose a novel representation learning model based on Short-Term Sequential Patterns for TKG reasoning, namely STSP. By modeling TKG sequences recurrently and learning representations of entities and relations. Specifically, the STSP encoder uses three main modules. Concurrent facts for each timestamp are modeled using a convolution-based relation-aware GCN. The entity-aware attention module is used to integrate the entity representation of the current timestamp and the previous timestamp. The sliding window mechanism is used to learn different relations sequentially. The entity and relation representations are then handed over to a translation-based decoder for final reasoning. We use four benchmark datasets to evaluate the proposed approach. The experimental results show that STSP out-performs state-of-the-art TKG reasoning methods and obtains substantial performance.

Temporal Knowledge Graph (TKG) representation learning aims to project entities and relations from high-dimensional spaces into low-dimensional ones while preserving dynamic relational characteristics. However, many existing methods primarily focus on single-time-stamp Knowledge Graphs, neglecting the importance of time in capturing the evolving relationships within TKGs. To address this limitation, we introduce TAR-TKG (Temporal-Aware Representation for Temporal Knowledge Graph), a novel framework that consists of three core modules. The first module, the Temporal Dynamics Steering Module, enhances dynamic temporal features by employing a multi-time-awareness network to capture changes between time stamps, thereby improving the understanding of temporal data evolution. The second module, the Cross-Time Domain Gating Module, applies cross-time domain graph convolution and adaptive gating to learn relationships between different time stamps, facilitating the integration of information across multiple time spans to improve the accuracy of temporal reasoning. The third module, the Temporal Adaptive Relation Perception Module, combines temporal embeddings, causal reasoning, and multi-modal relation fusion to enhance the model’s ability to perceive temporal relationships, particularly in managing causal dependencies and complex time-based interactions. Experimental results demonstrate that TAR-TKG outperforms existing baseline methods on three real-world datasets, proving its effectiveness in capturing dynamic relationship evolution and improving temporal reasoning within TKGs.

Temporal knowledge graph embedding via sparse transfer matrix

Few-shot link prediction for temporal knowledge graphs based on time-aware translation and attention mechanism

There has been an increasing interest in inferring future links on temporal knowledge graphs (KG). While links on temporal KGs vary continuously over time, the existing approaches model the temporal KGs in discrete state spaces. To this end, we propose a novel continuum model by extending the idea of neural ordinary differential equations (ODEs) to multi-relational graph convolutional networks. The proposed model preserves the continuous nature of dynamic multi-relational graph data and encodes both temporal and structural information into continuous-time dynamic embeddings. In addition, a novel graph transition layer is applied to capture the transitions on the dynamic graph, i.e., edge formation and dissolution. We perform extensive experiments on five benchmark datasets for temporal KG reasoning, showing our model’s superior performance on the future link forecasting task.

IoT devices generate substantial amounts of measurements and use many different formats to store this data. In order to make IoT devices interoperable, a number of ontologies have been developed, such as the Smart Applications REFerence (SAREF) ontology, to create knowledge graphs that can represent all kinds of measurements from IoT devices. We call the resulting knowledge graphs: IoT measurement knowledge graphs. In this thesis, we set out to investigate what differentiates IoT measurement knowledge graphs from regular knowledge graphs. In the first half, we describe in detail how to create IoT measurement knowledge graphs from real-world measurement data. In the second half, we investigate what happens when we use the graphs in different scenarios, with different methods and applications. In order to generate an IoT measurement knowledge graph, we create a mapping to transform the measurement data coming from IoT devices. We explore multiple ways to create this mapping and evaluate the resulting IoT measurement knowledge graph with competency questions. Using our mapping, we create OfficeGraph, by transforming IoT measurement data recorded over a year from 444 IoT devices located in an office building. This IoT measurement knowledge graph is validated by answering competency questions created with the support of the building owners, showing that we can answer questions we were not able to answer without it. Besides the entities, literals, and relations in knowledge graphs, the combination of these, the context of entities, provides additional knowledge. Therefore, if we want to use entities in knowledge graphs to train machine learning models, it would be a waste to take only the entities from the graph, because this would leave out information. Representation models, such as RDF2Vec and Graph Convolutional Networks (GCNs), can be used to learn (embedding) representations for entities that take context into account, creating a representation based on which relations, entities, and literals occur near the entity in the graph. We learn over IoT measurement knowledge graphs using multiple representation models and experiment with the effect of making more knowledge available to the representation models through semantic enrichment. This is done by making implicit information, such as (e.g.) consecutive measurements, explicitly available, by adding a relation between two measurements. Results show that the semantic enrichment has a positive effect on the learnability, based on the evaluation score, of the entity representations. Due to the dynamic nature of IoT measurement knowledge graphs, it is to be expected that new measurements are made after the initial IoT measurement knowledge graphs are created. Therefore, we investigate the possibility of estimating representations for new entities that are based on the existing entity representations. We introduce the embedding estimation method, which used the numerical attributes of entities, the measurement values, to find entities similar to the new entity. Then by averaging the embedding representations of those entities, it creates a new, estimated, embedding for the new entity. We perform experiments to test the embedding estimation method, and show that there is a trade-off between the amount of time saved by not re-training the entire pipeline, but also a decrease in accuracy, with the estimated embeddings. This thesis offers a focused research into IoT measurement knowledge graph. We provide insight into how IoT measurement knowledge graph can be created and how they differ from regular knowledge graphs, specifically in being numerical, dynamic, and shallow knowledge graphs. We suggest and validate remedies to the shallowness of IoT measurement knowledge graphs, through the semantic enrichments. Furthermore we show how the numerical aspect can be a strength, through the embedding estimation method, which can help with the dynamic nature of IoT measurement knowledge graph.

Knowledge Graph (KG) embedding approaches have been proved effective to infer new facts for a KG based on the existing ones–a problem known as KG completion. However, most of them have focused on static KGs, in fact, relational facts in KGs often show temporal dynamics, e.g., the fact (US, has president, Barack Obama, [2009–2017]) is only valid from 2009 to 2017. Therefore, utilizing available time information to develop temporal KG embedding models is an increasingly important problem. In this paper, we propose a new hyperplane-based time-aware KG embedding model for temporal KG completion. By employing the method of time-specific hyperplanes, our model could explicitly incorporate time information in the entity-relation space to predict missing elements in the KG more effectively, especially temporal scopes for facts with missing time information. Moreover, in order to model and infer four important relation patterns including symmetry, antisymmetry, inversion and composition, we map facts happened at the same time into a polar coordinate system. During training procedure, a time-enhanced negative sampling strategy is proposed to get more effective negative samples. Experimental results on datasets extracted from real-world temporal KGs show that our model significantly outperforms existing state-of-the-art approaches for the KG completion task.

Knowledge graph question answering is an important research direction for question answering tasks. In recent years, there has been an increasing amount of research on knowledge graph question answering, but temporal knowledge graph question answering is still a relatively unexplored area. In question answering tasks, many natural language questions have explicit or implicit temporal constraints, and most existing research methods lack the temporal awareness to deal with complex temporal questions. To address these challenges, this paper proposes a question answering model based on temporal knowledge graph embedding (TKGETQA). The model uses TKG embeddings to root a question in the entities, relations and time horizons it references, and perceives temporal information from the question to improve the accuracy of answer prediction. Experiments on the dataset CronQuestions in this paper show that the TKGETQA model exhibits better results compared to existing temporal knowledge graph question answering approaches.

Knowledge graphs’ reasoning is of great significance for the further development of artificial intelligence and information retrieval, especially for reasoning over temporal knowledge graphs. The rotation-based method has been shown to be effective at modeling entities and relations on a knowledge graph. However, due to the lack of temporal information representation capability, existing approaches can only model partial relational patterns and they cannot handle temporal combination reasoning. In this regard, we propose HTTR: Householder Transformation-based Temporal knowledge graph Reasoning, which focuses on the characteristics of relations that evolve over time. HTTR first fuses the relation and temporal information in the knowledge graph, then uses the Householder transformation to obtain an orthogonal matrix about the fused information, and finally defines the orthogonal matrix as the rotation of the head-entity to the tail-entity and calculates the similarity between the rotated vector and the vector representation of the tail entity. In addition, we compare three methods for fusing relational and temporal information. We allow other fusion methods to replace the current one as long as the dimensionality satisfies the requirements. We show that HTTR is able to outperform state-of-the-art methods in temporal knowledge graph reasoning tasks and has the ability to learn and infer all of the four relational patterns over time: symmetric reasoning, antisymmetric reasoning, inversion reasoning, and temporal combination reasoning.

Since the static Knowledge Graph cannot meet the dynamics of knowledge in the real world, Temporal Knowledge Graph has become a potential method for processing temporal knowledge. However, Temporal Knowledge Graph still faces the problem of incompleteness. Hence knowledge completion has become the main reasoning task for computing the missing facts in Knowledge Graph. In order to capture more richer historical information for predicting future events, we propose a new event forecasting model called Global-Recent Historical Network (GRHNet). In GRHNet, we use statistical methods to simulate the evolution of events. Furthermore, we design a global history learner to capture the repeatability of knowledge, and a recent history learner to capture time-variability of knowledge. GRHNet is evaluated on two benchmark datasets. The results demonstrate that, compared with state-of-the-art baselines, GRHNet achieves at least a 3% relative improvement in MRR.

Various temporal knowledge graph (KG) completion models have been proposed in the recent literature. The models usually contain two parts, a temporal embedding layer and a score function derived from existing static KG modeling approaches. Since the approaches differ along several dimensions, including different score functions and training strategies, the individual contributions of different temporal embedding techniques to model performance are not always clear. In this work, we systematically study six temporal embedding approaches and empirically quantify their performance across a wide range of configurations with about 4000 experiments and 19000 GPU hours. We classify the temporal embeddings into two classes: (1) timestamp embeddings and (2) time-dependent entity embeddings. Despite the common belief that the latter is more expressive, an extensive experimental study shows that timestamp embeddings can achieve on-par or even better performance with significantly fewer parameters. Moreover, we find that when trained appropriately, the relative performance differences between various temporal embeddings often shrink and sometimes even reverse when compared to prior results. For example, TTransE (Leblay and Chekol, 2018), one of the first temporal KG models, can outperform more recent architectures on ICEWS datasets. To foster further research, we provide the first unified open-source framework for temporal KG completion models with full composability, where temporal embeddings, score functions, loss functions, regularizers, and the explicit modeling of reciprocal relations can be combined arbitrarily.

A knowledge graph (KG) consists of numerous triples, in which each triple, i.e., (head entity, relation, tail entity), denotes a real-world assertion. Many large-scale KGs have been developed, e.g., general-purpose KGs Freebase and YAGO. Also, lots of domain-specific KGs are emerging, e.g., COVID-19 KGs, biomedical KGs, and agricultural KGs. By embedding KGs into low-dimensional vectors, i.e., representations of entities and relations, we could integrate KGs into machine learning models and enhance the performance of many prediction tasks, including search, recommendations, and question answering. During the construction, refinement, embedding, and application of KGs, a variety of KG learning algorithms have been developed to handle challenges in various real-world scenarios. Moreover, graph neural networks have also brought new opportunities to KG learning. This workshop aims to engage with active researchers from KG communities, recommendation communities, natural language processing communities, and other communities, and deliver state-of-the-art research insights into the core challenges in KG learning.