Bridging the gap between linked open data-based recommender systems and distributed representations

Linked open data in authoring virtual exhibitions

Unveiling the power of knowledge graph embedding in knowledge aware deep recommender systems for e-commerce: A comparative study

PurposeIn the last few years, the size of Linked Open Data (LOD) describing artworks, in general or domain-specific Knowledge Graphs (KGs), is gradually increasing. This provides (art-)historians and Cultural Heritage professionals with a wealth of information to explore. Specifically, structured data about iconographical and iconological (icon) aspects, i.e. information about the subjects, concepts and meanings of artworks, are extremely valuable for the state-of-the-art of computational tools, e.g. content recognition through computer vision. Nevertheless, a data quality evaluation for art domains, fundamental for data reuse, is still missing. The purpose of this study is filling this gap with an overview of art-historical data quality in current KGs with a focus on the icon aspects.Design/methodology/approachThis study’s analyses are based on established KG evaluation methodologies, adapted to the domain by addressing requirements from art historians’ theories. The authors first select several KGs according to Semantic Web principles. Then, the authors evaluate (1) their structures’ suitability to describe icon information through quantitative and qualitative assessment and (2) their content, qualitatively assessed in terms of correctness and completeness.FindingsThis study’s results reveal several issues on the current expression of icon information in KGs. The content evaluation shows that these domain-specific statements are generally correct but often not complete. The incompleteness is confirmed by the structure evaluation, which highlights the unsuitability of the KG schemas to describe icon information with the required granularity.Originality/valueThe main contribution of this work is an overview of the actual landscape of the icon information expressed in LOD. Therefore, it is valuable to cultural institutions by providing them a first domain-specific data quality evaluation. Since this study’s results suggest that the selected domain information is underrepresented in Semantic Web datasets, the authors highlight the need for the creation and fostering of such information to provide a more thorough art-historical dimension to LOD.

The World Wide Web is moving from a Web of hyper-linked documents to a Web of linked data. Thanks to the Semantic Web technological stack and to the more recent Linked Open Data (LOD) initiative, a vast amount of RDF data have been published in freely accessible datasets connected with each other to form the so called LOD cloud. As of today, we have tons of RDF data available in the Web of Data, but only a few applications really exploit their potential power. The availability of such data is for sure an opportunity to feed personalized information access tools such as recommender systems. We present an overview on recommender systems and we sketch how to use Linked Open Data to build a new generation of semantics-aware recommendation engines.

A review of recommender systems based on knowledge graph embedding

The World Wide Web is moving from a Web of hyper-linked Documents to a Web of linked Data. Thanks to the Semantic Web spread and to the more recent Linked Open Data (LOD) initiative, a vast amount of RDF data have been published in freely accessible datasets. These datasets are connected with each other to form the so called Linked Open Data cloud. As of today, there are tons of RDF data available in the Web of Data, but only few applications really exploit their potential power. In this paper we show how these data can successfully be used to develop a recommender system (RS) that relies exclusively on the information encoded in the Web of Data. We implemented a content-based RS that leverages the data available within Linked Open Data datasets (in particular DBpedia, Freebase and LinkedMDB) in order to recommend movies to the end users. We extensively evaluated the approach and validated the effectiveness of the algorithms by experimentally measuring their accuracy with precision and recall metrics.

Computing knowledge graph (KG) embeddings is a technique to learn distributional representations for components of a knowledge graph while preserving structural information. The learned embeddings can be used in multiple downstream tasks such as question answering, information extraction, query expansion, semantic similarity, and information retrieval. Over the past years, multiple embedding techniques have been proposed based on different underlying assumptions. The most actively researched models are translation-based which treat relations as translation operations in a shared (or relation-specific) space. Interestingly, almost all KG embedding models treat each triple equally, regardless of the fact that the contribution of each triple to the global information content differs substantially. Many triples can be inferred from others, while some triples are the foundational (basis) statements that constitute a knowledge graph, thereby supporting other triples. Hence, in order to learn a suitable embedding model, each triple should be treated differently with respect to its information content. Here, we propose a data-driven approach to measure the information content of each triple with respect to the whole knowledge graph by using rule mining and PageRank. We show how to compute triple-specific weights to improve the performance of three KG embedding models (TransE, TransR and HolE). Link prediction tasks on two standard datasets, FB15K and WN18, show the effectiveness of our weighted KG embedding model over other more complex models. In fact, for FB15K our TransE-RW embeddings model outperforms models such as TransE, TransM, TransH, and TransR by at least 12.98% for measuring the Mean Rank and at least 1.45% for HIT@10. Our HolE-RW model also outperforms HolE and ComplEx by at least 14.3% for MRR and about 30.4% for HIT@1 on FB15K. Finally, TransR-RW show an improvement over TransR by 3.90% for Mean Rank and 0.87% for HIT@10.

Knowledge Graph Embedding (KGE) is a technique used to capture structural information from Knowledge Graphs (KGs), enabling various downstream applications such as recommender system. KGE models trained on integrated KGs from multiple organizations tend to outperform those trained on a single KG, owing to the greater richness and diversity of information. Therefore, Federated Knowledge Graph Embedding (FKGE) emerges as a promising approach for privacy-preserving training of KGE models on KGs across organizations (clients). Existing FKGE framework learns a uniform global KGE model that achieves global optima by minimizing aggregated loss across clients. However, heterogeneity among KGs often leads to divergent local optima. This presents a fundamental trade-off: ensuring global optima can compromise local performance, while focusing on local optima can decrease global model utility. To overcome this, we propose Federated Local Adaptive Knowledge Graph Embedding (FedAdap) by drawing inspiration from partial federated learning. FedAdap employs a multilayer convolutional neural network, wherein its lower layers are shared across clients to learn shared information, it maps a seed KGE model into an alignment vector space representation. Its upper layers remain private, transforming the alignment vector space representation to an adaptive KGE model tailored to the local KG. Through this, FedAdap allows clients to leverage shared information while maintaining local adaptability and mitigating the impact of KGs heterogeneity. Experiments on data sets FB15k-237 and NELL-995 show that FedAdap outperforms its counterparts in link prediction tasks.

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.

Cloud manufacturing has emerged as a service-oriented paradigm, in which knowledge graphs (KGs) play a crucial role in enabling modularization and on-demand servitization by converting unstructured resources into a structured graph representation and factual knowledge for manufacturing tasks. KG embedding converts entities and relations into a low-dimensional space while expressing rich semantics of high-dimensional KGs. Existing works just focus on translating relations surrounding the nodes of graphs, while ignoring the applicability for modeling and inferring multiple relation patterns in the manufacturing context. Furthermore, the relative importance of complex manufacturing relations among different dimensions in embedded procedures has been ignored, leading to unclear representation learning of complex relations and entities in KGs. To overcome this issue, in this article, a novel relation and entropy weight-aware embedding model is proposed, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TransCE</i> . <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TransCE</i> performs coordinated transformations in vector space by normalizing the distance to integrate coordination. An entropy-based weighting method is also proposed to represent complex relations and entities surrounding the edges of graph embedding and assign the weighted value of relations to support the score function. Extended experiments are performed on several datasets, and a manufacturing indicates that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TransCE</i> shows remarkable improvement relative to baseline models.

With the popularity of Linked Open Data (LOD) and the associated rise in freely accessible knowledge that can be accessed via LOD, exploiting LOD for recommender systems has been widely studied based on various approaches such as graph-based or using different machine learning models with LOD-enabled features. Many of the previous approaches require construction of an additional graph to run graph-based algorithms or to extract path-based features by combining user-item interactions (e.g., likes, dislikes) and background knowledge from LOD. In this paper, we investigate Factorization Machines (FMs) based on particularly lightweight LOD-enabled features which can be directly obtained via a public SPARQL Endpoint without any additional effort to construct a graph. Firstly, we aim to study whether using FM with these lightweight LOD-enabled features can provide competitive performance compared to a learning-to-rank approach leveraging LOD as well as other well-established approaches such as kNN-item and BPRMF. Secondly, we are interested in finding out to what extent each set of LOD-enabled features contributes to the recommendation performance. Experimental evaluation on a standard dataset shows that our proposed approach using FM with lightweight LOD-enabled features provides the best performance compared to other approaches in terms of five evaluation metrics. In addition, the study of the recommendation performance based on different sets of LOD-enabled features indicate that property-object lists and PageRank scores of items are useful for improving the performance, and can provide the best performance through using them together for FM. We observe that subject-property lists of items does not contribute to the recommendation performance but rather decreases the performance.

In this article, we describe a hybrid recommender system (RS) in the artistic and cultural heritage area, which takes into account the activities on social media performed by the target user and her friends, and takes advantage of linked open data (LOD) sources. Concretely, the proposed RS (1) extracts information from Facebook by analyzing content generated by users and their friends; (2) performs disambiguation tasks through LOD tools; (3) profiles the active user as a social graph; (4) provides her with personalized suggestions of artistic and cultural resources in the surroundings of the user’s current location. The last point is performed by integrating collaborative filtering algorithms with semantic technologies in order to leverage LOD sources such as DBpedia and Europeana. Based on the recommended points of cultural interest, the proposed system is also able to suggest to the active user itineraries among them, which meet her preferences and needs and are sensitive to her physical and social contexts as well. Experimental results on real users showed the effectiveness of the different modules of the proposed recommender.

Knowledge Graph Embedding (KGE) is to learn continuous vectors of entities and relations in the Knowledge Graph (KG). Inspired by the R-GCN model, we propose a novel embedding learning model named RotatGAT, which combines the RotatE model and the GAT model. The goal is to overcome the shortcomings of R-GCN, that has a relatively high computing complexity and cannot distinguish the importance of neighbors. We introduce the RotatE model into RotatGAT to represent the embeddings of heterogeneous entities and relations in KG. Considering RotatE cannot use the structure information to learn entities' embeddings, we introduce the GAT model to learn the importance of neighbors of an entity and aggregate the feature information of neighbors for graph embedding learning. The link prediction experiments show the overall performance of RotatGAT on four benchmark datasets outperforms existing state-of-the-art models.

Knowledge graph (KG) embedding is to embed the entities and relations of a KG into a low-dimensional continuous vector space while preserving the intrinsic semantic associations between entities and relations. One of the most important applications of knowledge graph embedding (KGE) is link prediction (LP), which aims to predict the missing fact triples in the KG. A promising approach to improving the performance of KGE for the task of LP is to increase the feature interactions between entities and relations so as to express richer semantics between them. Convolutional neural networks (CNNs) have thus become one of the most popular KGE models due to their strong expression and generalization abilities. To further enhance favorable features from increased feature interactions, we propose a lightweight CNN-based KGE model called IntSE in this paper. Specifically, IntSE not only increases the feature interactions between the components of entity and relationship embeddings with more efficient CNN components but also incorporates the channel attention mechanism that can adaptively recalibrate channel-wise feature responses by modeling the interdependencies between channels to enhance the useful features while suppressing the useless ones for improving its performance for LP. The experimental results on public datasets confirm that IntSE is superior to state-of-the-art CNN-based KGE models for link prediction in KGs.

Recommendation systems are designed to uncover users’ potential preferences and make recommendations. However, they often face challenges such as data sparsity and the cold start problem. Although the introduction of knowledge graphs has partially addressed the issue of data sparsity, the challenge of cold start has not been effectively resolved. In this article, a novel approach called Social Perception with Graph Attention Network (SPGAT) for Recommendation is proposed. In SPGAT, we aim to leverage social perception to solve the cold start effectively for more accurate recommendations. The approach utilizes a multi-layer graph attention network to aggregate user preference features from collaborative knowledge graphs and social perception graphs. By analyzing the social network of a new user, associated friend users can be identified. The interaction data of these friend users is then provided as side information to recommend to the new user. To handle one-to-many and many-to-many relations, we introduce the TransD graph embedding model, which maps different types of relations and entities to different spaces. To optimize the proposed SPGAT, self-adversarial negative sampling is utilized to implement entity and relation embedding and generate negative samples. Experimental results demonstrate that SPGAT has achieved superior performance compared to several advanced methods.