SAQE: Complex Logical Query Answering via Semantic-Aware Representation Learning

Representation Learning (RL) of knowledge graphs aims to project both entities and relations into a continuous low dimensional space. There exits two kinds of representation methods for entities in Knowledge Graphs (KGs), including structure-based representation and description-based representation. Most methods represent entities with fact triples of KGs through translating embedding models, which can't integrate the rich information in entities descriptions with triple structure information. In this paper, we propose a novel RL method named as Representation Learning with Complete semantic Description of Knowledge Graphs (RLCD), which can exploit all semantic information of entity descriptions and fact triples of KGs, to enrich the semantic representations of KGs. More specifically, we explore Doc2Vec encoder model to encode all semantic information of entity descriptions without losing the relevance in the context of entities descriptions, and further learn knowledge representations from triples with entity descriptions. The experiment results show that RLCD gets better performance that state-of-the-art method DKRL, in terms of mean rank value and HITS. Moreover, RLCD is much faster than DKRL.

The representation learning of knowledge graph refers to embedding entities and relations in knowledge graph into a low-dimensional dense vector space. Existing knowledge graph embedding models mostly chose Euclidean Space as their vector space and consider each fact triple in knowledge graph independently. However, Euclidean Space is unable to represent knowledge effectively due to its strict constraints and mathematical expression. Besides, entities in knowledge graph are not isolated, while these models ignore the association between entities. To solve the problems above, we proposed a text-enhanced knowledge graph representation learning model in Hyperbolic Space. We utilize rich semantic information of entity description by using Transformer Encoder to enhance the ability of knowledge representation. Besides, we embed entities and relations into Hyperbolic Space, which can better capture hierarchical information of the knowledge graph. Experiments on benchmark dataset show that our method achieves better performance compared with other state-of-art methods.KeywordsKnowledge graphRepresentation learningEmbedding modelHyperbolic space

Knowledge graphs encode semantic knowledge that can be exploited to enhance different data-driven tasks, e.g., query answering, data mining, ranking or recommendation. However, knowledge graphs may be incomplete, and relevant relations may be not included in the graph, affecting accuracy of these data-driven tasks. We tackle the problem of relation discovery in a knowledge graph, and devise $$\mathcal {KOI}$$KOI, a semantic based approach able to discover relations in portions of knowledge graphs that comprise similar entities. $$\mathcal {KOI}$$KOI exploits both datatype and object properties to compute the similarity among entities, i.e., two entities are similar if their datatype and object properties have similar values. $$\mathcal {KOI}$$KOI implements graph partitioning techniques that exploit similarity values to discover relations from knowledge graph partitions. We conduct an experimental study on a knowledge graph of TED talks with state-of-the-art similarity measures and graph partitioning techniques. Our observed results suggest that $$\mathcal {KOI}$$KOI is able to discover missing edges between related TED talks that cannot be discovered by state-of-the-art approaches. These results reveal that combining semantics encoded both in the similarity measures and in the knowledge graph structure, has a positive impact on the relation discovery problem.

Entity-centric knowledge graphs (KGs) are now popular to collect facts about entities. KGs have rich schemas with a large number of different types and predicates to describe the entities and their relationships. On these rich schemas, logical rules are used to represent dependencies between the data elements. While rules are useful in query answering, data curation, and other tasks, they usually do not come with the KGs. Such rules have to be manually defined or discovered with the help of rule mining methods. We believe this rule-collection task should be done collectively to better capitalize our understanding of the data and to avoid redundant work conducted on the same KGs. For this reason, we introduce RuleHub , our extensible corpus of rules for public KGs. RuleHub provides functionalities for the archival and the retrieval of rules to all users, with an extensible architecture that does not constrain the KG or the type of rules supported. We are populating the corpus with thousands of rules from the most popular KGs and report on our experiments on automatically characterizing the quality of a rule with statistical measures.

The knowledge graph with relational abundant information has been widely used as the basic data support for the retrieval platforms. Image and text descriptions added to the knowledge graph enrich the node information, which accounts for the advantage of the multi-modal knowledge graph. In the field of cross-modal retrieval platforms, multi-modal knowledge graphs can help to improve retrieval accuracy and efficiency because of the abundant relational information provided by knowledge graphs. The representation learning method is significant to the application of multi-modal knowledge graphs. This paper proposes a distributed collaborative vector retrieval platform (DCRL-KG) using the multimodal knowledge graph VisualSem as the foundation to achieve efficient and high-precision multimodal data retrieval. Firstly, use distributed technology to classify and store the data in the knowledge graph to improve retrieval efficiency. Secondly, this paper uses BabelNet to expand the knowledge graph through multiple filtering processes and increase the diversification of information. Finally, this paper builds a variety of retrieval models to achieve the fusion of retrieval results through linear combination methods to achieve high-precision language retrieval and image retrieval. The paper uses sentence retrieval and image retrieval experiments to prove that the platform can optimize the storage structure of the multi-modal knowledge graph and have good performance in multi-modal space.

Entity representation learning is both fundamental and crucial for link prediction in knowledge graph. Existing entity representation learning approaches mainly focus on learning from knowledge triples with single modal text data which could only describe the things or concepts in words. However, multimodal data commonly exists in the real worlds and may describe things or concepts from different aspects. Therefore, multimodal entities have emerged in knowledge graph in recent years, which greatly enrich the knowledge graph by different information. This paper focuses on how to learn more robust and comprehensive representations of multimodal entities for better link prediction. A new representation learning method for multimodal entities is proposed, called Graph Attention with Bi-pooling Representation Learning (GBRL), where multimodal fusion and knowledge embedding are combined for learning representations of an entity with consideration of its multimodal neighbors. Firstly, feature vectors are obtained by pre-trained models for each modality. Then, the bilinear pooling is utilized for combining feature vectors of multimodal entities into multimodal feature vectors. A two-layer graph attention module is followed to generate multimodal representations of an entity from its multimodal neighbors. Finally, the inception decoder uses multimodal knowledge embedding to calculate scores for link prediction. The experimental results have shown that the proposed method performs well on link prediction by consideration of multimodal entities comparing with traditional methods that using only single modal text data.

There has been increasing research interest in inferring missing information from existing knowledge graphs (KGs) due to the emergence of a wide range of knowledge graph downstream applications such as question answering systems and search engines. Reasoning over knowledge graphs, which queries the correct entities only through a path consisting of multiple consecutive relations/hops from the starting entity, is an effective approach to do this task, but this topic has been rarely studied. As an attempt, the compositional training method equally treats the constructed multi-hop paths and one-hop relations to build training data, and then trains conventional knowledge graph completion models such as TransE in a compositional manner on the training data. However, it does not incorporate additional information along the paths during training, such as the intermediate entities and their types, which can be helpful to guide the reasoning towards the correct destination answers. Moreover, compositional training can only extend some existing models that can be composable, which significantly limits its applicability. Therefore, we design a novel model based on the recently proposed neural memory networks, which have large external memories and flexible writing/reading schemes, to address these problems. Specifically, we first introduce a single network layer, which is then used as the building block for a multi-layer neural network called TravNM, and a flexible memory updating method is developed to facilitate writing intermediate entity information during the multi-hop reasoning into memories. Finally, we conducted extensive experiments on large datasets, and the experimental results show the superiority of our proposed TravNM for reasoning over knowledge graphs with multiple hops.

Multi-modal knowledge graphs representation learning via multi-headed self-attention

Conducting complex logical queries over knowledge graphs remains a significant challenge. Recent research has successfully leveraged Pre-trained Language Models (PLMs) to tackle Knowledge Graph Complex Query Answering (KGCQA) tasks, which is attributed to PLMs' ability to comprehend logical semantics of queries through context learning. However, existing PLM-based KGCQA methods usually overlook the harm of disordered syntax or fragmented contexts within a serialized query, posing the problem of “impossible language” to limit PLMs in grasping the logical semantics. To address this problem, we propose a Progressive Prefix-Memory Tuning (PPMT) framework for KGCQA tasks, which effectively rectifies erroneous segments in serialized queries to assist PLMs in query answering. First, we propose a prefix-memory rectification mechanism embedded in a PLM module. This mechanism assigns rectification parameters in memory stores to polish the language segments of entities, relations, and queries through specific prefixes. To further capture the logical semantics in queries, we design a progressive fine-tuning strategy, which optimizes our model through a conditional gradient update process guided by knowledge translation constraints. Extensive experiments on widely used KGCQA benchmarks demonstrate the significant superiority of PPMT in terms of HR@3 and MRR. Our codes are available at https://github.com/lazyloafer/PPMT.

Numerous large knowledge graphs, such as DBpedia, Wikidata, Yago and Freebase, have been developed in the last decade, which contain millions of facts about various entities in the world. These knowledge graphs have proven to be incredibly useful for intelligent Web search, question understanding, in-context advertising, social media mining, and biomedicine. As some researchers have pointed out, a knowledge graph is not just a graph database, but it should have a layer of conceptual knowledge, which is usually represented as a set of first-order rules. However, it is challenging to automatically extract first-order rules from large knowledge graphs. In particular, traditional models are usually unable to handle rule learning in large knowledge graphs. This chapter aims to present state-of-the-art techniques and models on learning first-order rules using representation learning. By first recalling some basics of rule learning in knowledge graphs, we will introduce useful techniques of embedding-based rule learning through major models such as RLvLR and TyRuLe, which embed paths in knowledge graphs into latent spaces for candidate rule search. Then we evaluate the rule learning efficiency and the quality of automatically learned rules by applying them in link prediction. Before the chapter is concluded, we will also discuss some future research problems in the area.

In this chapter, we introduce the basic concept of a knowledge graph (KG). While a knowledge graph seems to be a very simple way of representing information, it turns out to be quite powerful and is almost a lingua franca of sorts between humans and machines. On the one hand, knowledge graphs, if constructed properly, contain much of the useful information that can be found in ‘natural language’ documents like newswire or even social media. On the other hand, machines can process knowledge graphs in a variety of ways, leading to applications and breakthroughs in areas like semantic search, question answering, entity resolution, and representation learning.

In conversational recommender systems (CRSs), conversations usually involve a set of items and item-related entities or attributes, e.g., director is a related entity of a movie. These items and item-related entities are often mentioned along the development of a dialog, leading to potential sequential dependencies among them. However, most of existing CRSs neglect these potential sequential dependencies. In this article, we first propose a Transformer-based sequential conversational recommendation method, named TSCR, to model the sequential dependencies in the conversations to improve CRS. In TSCR, we represent conversations by items and the item-related entities, and construct user sequences to discover user preferences by considering both the mentioned items and item-related entities. Based on the constructed sequences, we deploy a Cloze task to predict the recommended items along a sequence. Meanwhile, in certain domains, knowledge graphs formed by the items and their related entities are readily available, which provide various different kinds of associations among them. Given that TSCR does not benefit from such knowledge graphs, we then propose a knowledge graph enhanced version of TSCR, called TSCRKG. In specific, we leverage the knowledge graph to offline initialize our model TSCRKG, and augment the user sequence of conversations (i.e., sequence of the mentioned items and item-related entities in the conversation) with multi-hop paths in the knowledge graph. Experimental results demonstrate that our TSCR model significantly outperforms state-of-the-art baselines, and the enhanced version TSCRKG further improves recommendation performance on top of TSCR.

To conquer incompleteness of knowledge graphs (KGs), we focus on a relation prediction task that completes KGs by ranking all relationships between entities and selecting the top one. Most existing methods for relation prediction are representation-based models, which learn the structural information of KGs to obtain the embeddings of entities and relationships but fail to effectively use relation paths to predict potential relationships between two entities. The traditional path-based logical models consider the path characteristics but ignore the global semantics of entities in KGs, such as surrounding entities and relationships. In this paper, we propose path embedded hybrid reasoning model (PE-HRM), a novel reasoning mode based on logical reasoning, representation learning and neural network. PE-HRM considers structural characteristics of entities and path features between them and effectively fuses these features. Finally, we evaluate PE-HRM on datasets FB15K237 and NELL995. Experimental results show that PE-HRM significantly outperforms baseline models.

RuMER-RL: A hybrid framework for sparse knowledge graph explainable reasoning

Many important problems can be formulated as reasoning in knowledge graphs. Representation learning has proved extremely effective for transductive reasoning, in which one needs to make new predictions for already observed entities. This is true for both attributed graphs(where each entity has an initial feature vector) and non-attributed graphs (where the only initial information derives from known relations with other entities). For out-of-sample reasoning, where one needs to make predictions for entities that were unseen at training time, much prior work considers attributed graph. However, this problem is surprisingly under-explored for non-attributed graphs. In this paper, we study the out-of-sample representation learning problem for non-attributed knowledge graphs, create benchmark datasets for this task, develop several models and baselines, and provide empirical analyses and comparisons of the proposed models and baselines.