Retrofitting Soft Rules for Knowledge Representation Learning

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

Knowledge Graph Completion (KGC) is a popular topic in knowledge graph construction and related applications, aiming to complete the structure of knowledge graphs by predicting missing entities or relations and mining unknown facts in the knowledge graph. In the KGC task, Graph Neural Network (GNN)-based methods have achieved remarkable results due to their advantage of effectively capturing complex relations among entities and generating more accurate and rich entity representations by aggregating information from neighbouring nodes. These methods mainly focus on the representation of entities, and the representation of relations is obtained using simple dimensional transformations or initial embeddings. This treatment ignores the diversity and complex semantics of relations and restricts the efficiency of the model in utilizing relational information in the reasoning process. In this work, we propose the Relational Representation Augmented Graph Attention Network (RRA-GAT), which effectively identifies and weights neighbouring relations that actually contribute to the target relation by filtering out irrelevant information through an attention function based on the information and spatial domain. Furthermore, we capture complex patterns and features in the relational embedding by means of a feed-forward network consisting of a series of linear transformations and nonlinear activation functions. Experiments demonstrate the very advanced performance of RRA-GAT on the link prediction task on standard datasets FB15k-237 and WN18RR (e.g., improved the MRR metric on the WN18RR dataset by 7.8% relative improvement).

Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embedding vectors. These methods have recently been applied to KG link prediction and question answering over incomplete KGs (KGQA). KGEs typically create an embedding for each entity in the graph, which results in large model sizes on real-world graphs with millions of entities. For downstream tasks these atomic entity representations often need to be integrated into a multi stage pipeline, limiting their utility. We show that an off-the-shelf encoder-decoder Transformer model can serve as a scalable and versatile KGE model obtaining state-of-the-art results for KG link prediction and incomplete KG question answering. We achieve this by posing KG link prediction as a sequence-to-sequence task and exchange the triple scoring approach taken by prior KGE methods with autoregressive decoding. Such a simple but powerful method reduces the model size up to 98% compared to conventional KGE models while keeping inference time tractable. After finetuning this model on the task of KGQA over incomplete KGs, our approach outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.

Neuro-Symbolic Artificial Intelligence (AI) focuses on integrating symbolic and sub-symbolic systems to enhance the performance and explainability of predictive models. Symbolic and sub-symbolic approaches differ fundamentally in how they represent data and make use of data features to reach conclusions. Neuro-symbolic systems have recently received significant attention in the scientific community. However, despite efforts in neural-symbolic integration, symbolic processing can still be better exploited, mainly when these hybrid approaches are defined on top of knowledge graphs. This work is built on the statement that knowledge graphs can naturally represent the convergence between data and their contextual meaning (i.e., knowledge). We propose a hybrid system that resorts to symbolic reasoning, expressed as a deductive database, to augment the contextual meaning of entities in a knowledge graph, thus, improving the performance of link prediction implemented using knowledge graph embedding (KGE) models. An entity context is defined as the ego network of the entity in a knowledge graph. Given a link prediction task, the proposed approach deduces new RDF triples in the ego networks of the entities corresponding to the heads and tails of the prediction task on the knowledge graph (KG). Since knowledge graphs may be incomplete and sparse, the facts deduced by the symbolic system not only reduce sparsity but also make explicit meaningful relations among the entities that compose an entity ego network. As a proof of concept, our approach is applied over a KG for lung cancer to predict treatment effectiveness. The empirical results put the deduction power of deductive databases into perspective. They indicate that making explicit deduced relationships in the ego networks empowers all the studied KGE models to generate more accurate links.

Knowledge graphs display various entities and their relationships in the real world based on knowledge representation and can analyze and predict the intrinsic relationship between knowledge embeddings through data mining and information processing, which are widely used in search engines, web analytics and smart recommendation areas. As existing knowledge graph information is continuously created and grown, it is a curial task to determine whether the information in knowledge graph is correct and to complete the missing information. In response to this challenge, the researchers proposed a number of graph convolutional network (GCN)-based models to characterize knowledge graphs. The state-of-the-art model is R-GCN, which can effectively extract features. This paper deeply studies the algorithm ideas and results of the R-GCN model, explores whether the model can be further optimized in entity classification and link prediction, and finally, improves the original model and proposes a relational aggregation graph convolutional network. Specifically, this paper finds that a subset of the set of entities may be directly connected to a central entity. All the entities in this subset possess partially identical attributes. At the same time, the relationships between these entities and the central entity may be similar. These similar attributes and relationships can be abstractly aggregated into virtual entities and virtual relationships, respectively, to better extract the topological relationship features. This paper uses the FB15k dataset to evaluate the performance of the proposed model on knowledge graph completion tasks. The experimental results show that the proposed RA-GCN model achieves a certain level improvement compared with the original model and that it can extract knowledge graph topological relationship characteristics more effectively.

Knowledge Graph Completion (KGC) is an essential task aimed at mitigating the issue of incompleteness in knowledge graphs, thereby enhancing their utility for various downstream applications. Existing KGC models predominantly fall into two categories: structure-based and semantic-based approaches. Structure-based methods often encounter challenges with long-tail entities due to the scarcity of structural information and imbalanced entity distributions. Conversely, semantic-based methods, while addressing those limitations, necessitate extensive training of language models and specific finetuning for each knowledge graph, thus constraining their practical efficiency. To alleviate those limitations in both approaches, in this paper, we propose KICGPTv2, an innovative framework that synergizes a large language model (LLM) with traditional KGC methods. This integration effectively mitigates the long-tail entity problem without incurring significant additional training overhead. Central to the KICGPTv2 model is a novel in-context learning strategy, termed Knowledge Prompt, which encodes structural knowledge into demonstrations to effectively guide the LLM. Comprehensive evaluations on various KGC tasks, including link prediction, relation prediction, and triple classification, underscore the efficacy of the KICGPTv2 model, highlighting its ability to achieve competitive performance with reduced training demands and without the need for finetuning

Knowledge graph embedding models are used to learn low‐dimensional representations of entities and relations in knowledge graphs. In this paper, we propose Multi‐RAttE, an attention‐based learning method for multiple relational knowledge graph embedding representation, which divides the information transfer in the knowledge graph into cross‐relational information transfer and relation‐specific information transfer, and divides the embedding of knowledge graph entities into structural embedding and multi‐relational embedding for joint learning. To objectively analyse the performance of the Multi‐RAttE model, we select two typical datasets and different representative baseline models for experimental evaluation on several tasks such as link prediction, multi‐relation prediction and node classification. The experimental results show that the Multi‐RAttE model improves 8% over the state‐of‐the‐art model Composition‐based Multi‐Relational Graph Convolutional Networks (CompGCN) in terms of Hits@1 metric on the link prediction task on FB15k‐237 dataset; on the multi‐relation prediction task, the accuracy improves by 1.8% and 3.7% in the auc metric and F1 metric, respectively. The experimental results have proved that the Multi‐RAttE model can effectively perform the representation of multiple relations.

As research on utilizing human knowledge in natural language processing has attracted considerable attention in recent years, knowledge graph (KG) completion has come into the spotlight. Recently, a new knowledge graph completion method using a pre-trained language model, such as KG-BERT, is presented and showed high performance. However, its scores in ranking metrics such as Hits@k are still behind state-of-the-art models. We claim that there are two main reasons: 1) failure in sufficiently learning relational information in knowledge graphs, and 2) difficulty in picking out the correct answer from lexically similar candidates. In this paper, we propose an effective multi-task learning method to overcome the limitations of previous works. By combining relation prediction and relevance ranking tasks with our target link prediction, the proposed model can learn more relational properties in KGs and properly perform even when lexical similarity occurs. Experimental results show that we not only largely improve the ranking performances compared to KG-BERT but also achieve the state-of-the-art performances in Mean Rank and Hits@10 on the WN18RR dataset.

Affective knowledge graph constructs the objective world from the perspective of knowledge representation learning, and has certain reasoning and analysis capabilities. The reasoning analysis of the objective world includes intention analysis. The action and behavior route of the intention analysis is constructed as an event knowledge graph, and the relationship between the nodes in the event knowledge graph is used to explain the intention, and the intention analysis task can be completed by constructing the knowledge representation. However, in intention analysis, the number of actions and the position of actions in the overall action route are important indicators in the task of intention analysis. However, most of the knowledge graphs are two-node relationships, and the study of the position of nodes in the relationship only considers Symmetrical relationship. Aiming at the problem, a representation model of super nodes is proposed, in which information is integrated into the model, and attention is paid to network data set to test knowledge link prediction tasks. Experiments show that the model also achieves good results in the link prediction task.

Learning structured embeddings of knowledge graphs with generative adversarial framework

Knowledge graph completion is an important research issue in knowledge graph construction, knowledge engineering, and natural language processing. A knowledge graph is a knowledge support for realizing accurate knowledge services in general and professional fields. It is also an important breakthrough foundation in information retrieval, question-and-answer interactions, and information recommendation. The low quality and small scale of the knowledge graph are the main bottlenecks that hinder its wide applications. The purpose of knowledge graph completion is to build a large-scale and high-quality knowledge graph for continuously updating and expanding the knowledge graph. Aiming at the difficulty of knowledge graph completion methods to extract deep semantic features from auxiliary information, such as unstructured texts, this study proposes a knowledge graph completion method based on parsing graph embedding and weighted graph convolutional network. This method uses the weighted graph convolutional network to model the semantic dependency parsing of the entity description and construct the semantic dependency parsing graph embedding. Furthermore, it introduces a multi-grained sentence-embedding generation method of the entity description, which is intended to build entity representation learning that can capture multi-grained semantics and deep-level semantic features. The experimental results on two public datasets show that the proposed knowledge graph completion approach outperforms the existing methods, thereby demonstrating its effectiveness and superiority.

Knowledge graphs have shown increasing value in semantic search, intelligent Q&A, data analysis, natural language processing, visual understanding, IoT devices, etc. It is undeniable that knowledge graphs have become the mandatory path for the artificial intelligence fields development. However, the information contained in existing knowledge graphs is incomplete, which attracts a large number of researchers to enhance the completeness of knowledge graphs utilizing knowledge graph completion methods. Most traditional embedding-based knowledge graph completion models use structural information within data-rich triples from the knowledge graph is limited by the long-tail distribution of the relations in the triples. To address this problem, we propose a Bert-based knowledge graph completion algorithm for few-shot knowledge graphs, with the main goal of implementing the knowledge graph completion task with only a few sample triples of training instances. We improve the baseline model GMatching for handling few-shot knowledge graphs by introducing the Bert pre-trained linguistic representation model to enhance the semantic representation of entities and relations in the triples. Through experiments, we demonstrate that our improved model B-GMatching achieves good results.

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.

The representation learning in knowledge graph aims to embed the semantic information of the research object into dense low dimensional distributed real valued vectors. The classical knowledge representation model, TransR, uses the relation specific matrix to represent the entities and relations in different semantic spaces, so as to solve the separation problem of semantic space. However, the TransR model only considers the different types of relations, ignores the entity types, and has defects in the processing of inverse relations. To solve the model problems, a novel knowledge representation method for multiple pattern embeddings based on entity-relation mapping matrix (M-TransER) is presented. The M-TransER model introduces the entity-relation mapping matrix, which makes the model consider the entity type while considering the relation type. On the basis that entities and relations are modeled as positive translation geometric distance, the inverse translation geometric distance model and the symmetrical relation model are fused. Eliminate the defects of the model in dealing with inverse relations, and improve the efficiency of symmetric relation processing. Experimental results on open datasets show that the M-TransER model has made great progress and demonstrated its superiority over the existing models and methods in both link prediction and triple classification tasks.

Knowledge graphs (KGs) are important resources for a variety of natural language processing tasks but suffer from incompleteness. To address this challenge, a number of knowledge graph completion (KGC) methods have been developed using low-dimensional graph embeddings. Most existing methods focus on the structured information of triples in encyclopaedia KG and maximize the likelihood of them. However, they neglect semantic information contained in lexical KG. To overcome this drawback, we propose a novel KGC method (named as TransC), that integrates the structured information in encyclopaedia KG and the entity concepts in lexical KG, which describe the categories of entities. Since all entities appearing in the head (or tail) position with the same relation have some common concepts, we introduce a novel semantic similarity to measure the distinction of entity semantics with the concept information. And then TransC utilizes concept-based semantic similarity of the related entities and relations to capture prior distributions of entities and relations. With the concept-based prior distributions, TransC generates multiple embedding representations of each entity in different contexts and estimates the posterior probability of entity and relation prediction. Experimental results demonstrate the efficiency of the proposed method on two benchmark datasets.