Accepted Papers

Multi-view Knowledge Graph Embedding for Entity Alignment

Qingheng Zhang (Nanjing University), Zequn Sun (Nanjing University), Wei Hu (Nanjing University), Muhao Chen (University of Pennsylvania), Lingbing Guo (Nanjing University) and Yuzhong Qu (Nanjing University).

Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao (CN), pp5429-5435, 2019

Abstract. We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, a vast of entity features are still unexplored or not equally treated together, which impairs the accuracy and robustness of embedding-based entity alignment. In this paper, we propose a novel framework that unifies multiple views of entities to learn embeddings for entity alignment. Specifically, we embed entities based on the views of entity names, relations and attributes, with several combination strategies. Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs. Our experiments on real-world datasets show that the proposed framework significantly outperforms the state-of-the-art embedding-based entity alignment methods. The selected views, cross-KG inference and combination strategies all contribute to the performance improvement.

Url:  https://doi.org/10.24963/ijcai.2019/754
No:  472

Enriching Knowledge Bases with Interesting Negative Statements

Hiba Arnaout (Max Planck Institute for Informatics), Simon Razniewski (Max Planck Institute for Informatics) and Gerhard Weikum (Max Planck Institute for Informatics).

Proc. 1^st Automated Knowledge Base Construction conference (AKBC) 2020

Abstract. Knowledge bases (KBs), pragmatic collections of knowledge about notable entities, are an important asset in applications such as search, question answering and dialogue. Rooted in a long tradition in knowledge representation, all popular KBs only store positive information, but abstain from taking any stance towards statements not contained in them. In this paper, we make the case for explicitly stating interesting statements which are not true. Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking. We introduce two approaches towards automatically compiling negative statements. (i) In peer-based statistical inferences, we compare entities with highly related entities in order to derive potential negative statements, which we then rank using supervised and unsupervised features. (ii) In pattern-based query log extraction, we use a pattern-based approach for harvesting search engine query logs. Experimental results show that both approaches hold promising and complementary potential. Along with this paper, we publish the first datasets on interesting negative information, containing over 1.4M statements for 130K popular Wikidata entities.

URL:  https://akbc.ws/2020/papers/pSLmyZKaS
No:  473

Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs

Yuting Wu (Peking University), Xiao Liu (Peking University), Yansong Feng (Peking University), Zheng Wang (University of Leeds), Rui Yan (Peking University) and Dongyan Zhao (Peking University).

Proc. 28th International Joint Conference on Artificial Intelligence (IJCAI), Macao (CN), pp5278-5284, 2019

Abstract. Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods. Such approaches work by learning KG representations so that entity alignment can be performed by measuring the similarities between entity embeddings. While promising, prior works in the field often fail to properly capture complex relation information that commonly exists in multi-relational KGs, leaving much room for improvement. In this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations. Experiments on three real-world cross-lingual datasets show that our approach delivers better and more robust results over the state-of-the-art alignment methods by learning better KG representations.

URL:  https://doi.org/10.24963/ijcai.2019/733
No:  475

Representation Learning for Attributed Multiplex Heterogeneous Network

Yukuo Cen (Tsinghua University), Xu Zou (Tsinghua University), Jianwei Zhang (Alibaba Group), Hongxia Yang (Alibaba Group), Jingren Zhou (Alibaba Group) and Jie Tang (Tsinghua University).

Proc. 25^th ACM SIGKDD international conference on knowledge discovery and data mining (KDD), Anchorage (US), pp1358-1368, 2019

Abstract. Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist of billions of nodes and edges of multiple types and each node is associated with different attributes. In this paper, we formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. The framework supports both transductive and inductive learning. We also give the theoretical analysis of the proposed framework, showing its connection with previous works and proving its better generalization ability. We conduct systematical evaluations for the proposed framework on four different genres of challenging datasets: Amazon, YouTube, Twitter, and Alibaba. Experimental results demonstrate that with the learned embeddings from the proposed framework, we can achieve statistically significant improvements (e.g., 5.99-28.23% lift by F1 scores; p<<0.01, t-test) over previous state-of-the-arts for link prediction. The framework has also been successfully deployed on the recommendation system of a worldwide leading E-Commerce company, Alibaba Group. Results of the online A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice.

URL:  https://dl.acm.org/doi/10.1145/3292500.3330964 / https://arxiv.org/abs/1905.01669
No:  479

Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules

Ernesto Jimenez-Ruiz (City, University of London), Asan Agibetov (Medical University of Vienna), Jiaoyan Chen (University of Oxford), Matthias Samwald (Medical University of Vienna, Austria) and Valerie Cross (Miami University).

Proc. 24^th European conference on artificial intelligence (ECAI), Santiago de Compostella (ES), pp784-791, 2020

Abstract. Large ontologies still pose serious challenges to state-of-the-art ontology alignment systems. In this paper we present an approach that combines a neural embedding model and logic-based modules to accurately divide an input  ontology matching task into smaller and more tractable matching (sub)tasks. We have conducted a comprehensive evaluation using the datasets of the Ontology Alignment Evaluation Initiative. The results are encouraging and suggest that the proposed method is adequate in practice and can be integrated within the workflow of systems unable to cope with very large ontologies.

URL:  http://ecai2020.eu/papers/792_paper.pdf / https://arxiv.org/abs/2003.05370
No:  483

Learning Triple Embeddings from Knowledge Graphs

Valeria Fionda (University of Calabria) and Giuseppe Pirrò (Sapienza University of Rome).

Proc. Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), New-York city (US), pp3874-3881, 2020

Abstract. Graph embedding techniques allow to learn high-quality feature vectors from graph structures and are useful in a variety of tasks, from node classification to clustering. Existing approaches have only focused on learning feature vectors for the nodes and predicates in a knowledge graph. To the best of our knowledge, none of them has tackled the problem of directly learning triple embeddings. The approaches that are closer to this task have focused on homogeneous graphs involving only one type of edge and obtain edge embeddings by applying some operation (e.g., average) on the embeddings of the endpoint nodes. The goal of this paper is to introduce Triple2Vec, a new technique to directly embed knowledge graph triples. We leverage the idea of line graph of a graph and extend it to the context of knowledge graphs. We introduce an edge weighting mechanism for the line graph based on semantic proximity. Embeddings are finally generated by adopting the SkipGram model, where sentences are replaced with graph walks. We evaluate our approach on different real-world knowledge graphs and compared it with related work. We also show an application of triple embeddings in the context of user-item recommendations.

URL:  https://doi.org/10.1609/aaai.v34i04.5800  / https://arxiv.org/abs/1905.11691v1
No:  491

Adaptive Low-level Storage of Very Large Knowledge Graphs

Jacopo Urbani (Vrije Universiteit Amsterdam) and Ceriel Jacobs (Vrije Universiteit Amsterdam).

Proceedings of The Web Conference (29th International World Wide Web Conference). Taipei (TW), pp. 1761-1772, 2020

Abstract. The increasing availability and usage of Knowledge Graphs (KGs) on the Web calls for scalable and general-purpose solutions to store this type of data structures. We propose Trident, a novel storage architecture for very large KGs on centralized systems. Trident uses several interlinked data structures to provide fast access to nodes and edges, with the physical storage changing depending on the topology of the graph to reduce the memory footprint. In contrast to single architectures designed for single tasks, our approach offers an interface with few low-level and general-purpose primitives that can be used to implement tasks like SPARQL query answering, reasoning, or graph analytics. Our experiments show that Trident can handle graphs with 10^11 edges using inexpensive hardware, delivering competitive performance on multiple workloads.

URL:  https://dl.acm.org/doi/10.1145/3366423.3380246 / https://arxiv.org/abs/2001.09078
No:  503

Stream Reasoning Agents

Riccardo Tommasini (University of Tartu), Davide Calvaresi (University of Applied Sciences Western Switzerland) and Jean-Paul Calbimonte (University of Applied Sciences and Arts Western Switzerland HES-SO).

Proc. 18th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), Montréal (CA), pp. 1664-1680. 2019

Abstract. Data streams are increasingly needed for different types of applications and domains, where dynamicity and data velocity are of foremost importance. In this context, research challenges raise regarding the generation, publication, processing, and discovery of these streams, especially in distributed, heterogeneous and collaborative environments such as the Web. Stream reasoning has addressed some of these challenges in the last decade, presenting a novel data processing paradigm that lays at the intersection among semantic data modeling, stream processing, and inference techniques. However, stream reasoning works have focused almost exclusively on architectures and approaches that assume an isolated processing environment. Therefore, they lack, in general, the means for discovering, collaborating, negotiating, sharing, or validating data streams on a highly heterogeneous ecosystem as the Web. Agents and multi-agent systems research has long developed principles and foundations for enabling some of these features, although usually under assumptions that require to be revised in order to comply with the characteristics of data streams. This paper presents a vision for a Web of stream reasoning agents, capable of sharing not only streaming data, but also processing duties, using collaboration and negotiation protocols, while relying on common vocabularies and protocols that take into account the high dynamicity of their knowledge, goals, and behavioral patterns.

URL:   https://dl.acm.org/doi/abs/10.5555/3306127.3331894 / http://publications.hevs.ch/index.php/publications/show/2522