Semantic Networks
KGxBoard: Explainable and Interactive Leaderboard for Evaluation of Knowledge Graph Completion Models
Widjaja, Haris, Gashteovski, Kiril, Rim, Wiem Ben, Liu, Pengfei, Malon, Christopher, Ruffinelli, Daniel, Lawrence, Carolin, Neubig, Graham
Knowledge Graphs (KGs) store information in the form of (head, predicate, tail)-triples. To augment KGs with new knowledge, researchers proposed models for KG Completion (KGC) tasks such as link prediction; i.e., answering (h; p; ?) or (?; p; t) queries. Such models are usually evaluated with averaged metrics on a held-out test set. While useful for tracking progress, averaged single-score metrics cannot reveal what exactly a model has learned -- or failed to learn. To address this issue, we propose KGxBoard: an interactive framework for performing fine-grained evaluation on meaningful subsets of the data, each of which tests individual and interpretable capabilities of a KGC model. In our experiments, we highlight the findings that we discovered with the use of KGxBoard, which would have been impossible to detect with standard averaged single-score metrics.
Large-scale Entity Alignment via Knowledge Graph Merging, Partitioning and Embedding
Xin, Kexuan, Sun, Zequn, Hua, Wen, Hu, Wei, Qu, Jianfeng, Zhou, Xiaofang
Entity alignment is a crucial task in knowledge graph fusion. However, most entity alignment approaches have the scalability problem. Recent methods address this issue by dividing large KGs into small blocks for embedding and alignment learning in each. However, such a partitioning and learning process results in an excessive loss of structure and alignment. Therefore, in this work, we propose a scalable GNN-based entity alignment approach to reduce the structure and alignment loss from three perspectives. First, we propose a centrality-based subgraph generation algorithm to recall some landmark entities serving as the bridges between different subgraphs. Second, we introduce self-supervised entity reconstruction to recover entity representations from incomplete neighborhood subgraphs, and design cross-subgraph negative sampling to incorporate entities from other subgraphs in alignment learning. Third, during the inference process, we merge the embeddings of subgraphs to make a single space for alignment search. Experimental results on the benchmark OpenEA dataset and the proposed large DBpedia1M dataset verify the effectiveness of our approach.
Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision
Kalinowski, Alexander, An, Yuan
The majority of knowledge graph embedding techniques treat entities and predicates as separate embedding matrices, using aggregation functions to build a representation of the input triple. However, these aggregations are lossy, i.e. they do not capture the semantics of the original triples, such as information contained in the predicates. To combat these shortcomings, current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. In this paper, we design a novel fine-tuning approach for learning triple embeddings by creating weak supervision signals from pre-trained knowledge graph embeddings. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations. We evaluate the proposed method on two widely studied knowledge graphs and show consistent improvement over other state-of-the-art triple embedding methods on triple classification and triple clustering tasks.
A Knowledge Graph-Enhanced Tensor Factorisation Model for Discovering Drug Targets
Ye, Cheng, Swiers, Rowan, Bonner, Stephen, Barrett, Ian
The drug discovery and development process is a long and expensive one, costing over 1 billion USD on average per drug and taking 10-15 years. To reduce the high levels of attrition throughout the process, there has been a growing interest in applying machine learning methodologies to various stages of drug discovery and development in the recent decade, especially at the earliest stage identification of druggable disease genes. In this paper, we have developed a new tensor factorisation model to predict potential drug targets (genes or proteins) for treating diseases. We created a three dimensional data tensor consisting of 1,048 gene targets, 860 diseases and 230,011 evidence attributes and clinical outcomes connecting them, using data extracted from the Open Targets and PharmaProjects databases. We enriched the data with gene target representations learned from a drug discovery oriented knowledge graph and applied our proposed method to predict the clinical outcomes for unseen gene target and disease pairs. We designed three evaluation strategies to measure the prediction performance and benchmarked several commonly used machine learning classifiers together with Bayesian matrix and tensor factorisation methods. The result shows that incorporating knowledge graph embeddings significantly improves the prediction accuracy and that training tensor factorisation alongside a dense neural network outperforms all other baselines. In summary, our framework combines two actively studied machine learning approaches to disease target identification, namely tensor factorisation and knowledge graph representation learning, which could be a promising avenue for further exploration in data driven drug discovery.
Knowledge Graph Curation: A Practical Framework
Knowledge Graphs (KGs) have shown to be very important for applications such as personal assistants, question-answering systems, and search engines. Therefore, it is crucial to ensure their high quality. However, KGs inevitably contain errors, duplicates, and missing values, which may hinder their adoption and utility in business applications, as they are not curated, e.g., low-quality KGs produce low-quality applications that are built on top of them. In this vision paper, we propose a practical knowledge graph curation framework for improving the quality of KGs. First, we define a set of quality metrics for assessing the status of KGs, Second, we describe the verification and validation of KGs as cleaning tasks, Third, we present duplicate detection and knowledge fusion strategies for enriching KGs. Furthermore, we give insights and directions toward a better architecture for curating KGs.
Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries
Liu, Xiao, Zhao, Shiyu, Su, Kai, Cen, Yukuo, Qiu, Jiezhong, Zhang, Mengdi, Wu, Wei, Dong, Yuxiao, Tang, Jie
Knowledge graph (KG) embeddings have been a mainstream approach for reasoning over incomplete KGs. However, limited by their inherently shallow and static architectures, they can hardly deal with the rising focus on complex logical queries, which comprise logical operators, imputed edges, multiple source entities, and unknown intermediate entities. In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies. We design a KG triple transformation method to enable Transformer to handle KGs, which is further strengthened by the Mixture-of-Experts (MoE) sparse activation. We then formulate the complex logical queries as masked prediction and introduce a two-stage masked pre-training strategy to improve transferability and generalizability. Extensive experiments on two benchmarks demonstrate that kgTransformer can consistently outperform both KG embedding-based baselines and advanced encoders on nine in-domain and out-of-domain reasoning tasks. Additionally, kgTransformer can reason with explainability via providing the full reasoning paths to interpret given answers.
VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion
He, Tao, Liu, Ming, Cao, Yixin, Jiang, Tianwen, Zheng, Zihao, Zhang, Jingrun, Zhao, Sendong, Qin, Bing
Knowledge Graph Completion (KGC) aims to reason over known facts and infer missing links but achieves weak performances on those sparse Knowledge Graphs (KGs). Recent works introduce text information as auxiliary features or apply graph densification to alleviate this challenge, but suffer from problems of ineffectively incorporating structure features and injecting noisy triples. In this paper, we solve the sparse KGC from these two motivations simultaneously and handle their respective drawbacks further, and propose a plug-and-play unified framework VEM$^2$L over sparse KGs. The basic idea of VEM$^2$L is to motivate a text-based KGC model and a structure-based KGC model to learn with each other to fuse respective knowledge into unity. To exploit text and structure features together in depth, we partition knowledge within models into two nonoverlapping parts: expressiveness ability on the training set and generalization ability upon unobserved queries. For the former, we motivate these two text-based and structure-based models to learn from each other on the training sets. And for the generalization ability, we propose a novel knowledge fusion strategy derived by the Variational EM (VEM) algorithm, during which we also apply a graph densification operation to alleviate the sparse graph problem further. Our graph densification is derived by VEM algorithm. Due to the convergence of EM algorithm, we guarantee the increase of likelihood function theoretically with less being impacted by noisy injected triples heavily. By combining these two fusion methods and graph densification, we propose the VEM$^2$L framework finally. Both detailed theoretical evidence, as well as qualitative experiments, demonstrates the effectiveness of our proposed framework.
Stardog Strengthens Enterprise-Grade Security to Knowledge Graph in the Cloud
Stardog, the leading Enterprise Knowledge Graph platform provider, announced it has achieved System and Organization Controls (SOC) 2 Type 1 compliance, demonstrating the company's commitment to providing the most robust data security and privacy for its growing customer base. The SOC 2 Type I audit, conducted by Riskpro, is an independent review assessing Stardog's internal controls involving security, availability, and confidentiality of the data processed on behalf of its customers. A widely recognized auditing standard developed by the American Institute of Certified Public Accounts (AICPA), SOC 2 compliance confirms Stardog's controls and processes meet AICPA Trust Service Criteria. "As enterprise organizations use knowledge graph in the cloud to help them democratize data access and scale analytics insight, they need confidence that their data is secure," said Mike Grove, SVP, Engineering & Information Security of Stardog. "Achieving SOC 2 Type 1 certification eliminates the burden on our customers of securing data, allowing them to focus on driving business outcomes."
Enriching Wikidata with Linked Open Data
Zhang, Bohui, Ilievski, Filip, Szekely, Pedro
Large public knowledge graphs, like Wikidata, contain billions of statements about tens of millions of entities, thus inspiring various use cases to exploit such knowledge graphs. However, practice shows that much of the relevant information that fits users' needs is still missing in Wikidata, while current linked open data (LOD) tools are not suitable to enrich large graphs like Wikidata. In this paper, we investigate the potential of enriching Wikidata with structured data sources from the LOD cloud. We present a novel workflow that includes gap detection, source selection, schema alignment, and semantic validation. We evaluate our enrichment method with two complementary LOD sources: a noisy source with broad coverage, DBpedia, and a manually curated source with a narrow focus on the art domain, Getty. Our experiments show that our workflow can enrich Wikidata with millions of novel statements from external LOD sources with high quality. Property alignment and data quality are key challenges, whereas entity alignment and source selection are well-supported by existing Wikidata mechanisms. We make our code and data available to support future work.
Evaluating and improving social awareness of energy communities through semantic network analysis of online news
Piselli, C., Colladon, A. Fronzetti, Segneri, L., Pisello, A. L.
The implementation of energy communities represents a cross-disciplinary phenomenon that has the potential to support the energy transition while fostering citizens' participation throughout the energy system and their exploitation of renewables. An important role is played by online information sources in engaging people in this process and increasing their awareness of associated benefits. In this view, this work analyses online news data on energy communities to understand people's awareness and the media importance of this topic. We use the Semantic Brand Score (SBS) indicator as an innovative measure of semantic importance, combining social network analysis and text mining methods. Results show different importance trends for energy communities and other energy and society-related topics, also allowing the identification of their connections. Our approach gives evidence to information gaps and possible actions that could be taken to promote a low-carbon energy transition.