Knowledge Graphs are graph structures that capture knowledge in the form of entities and the relationships between them, and optionally the provenance information. Along with Semantic Web standards such as RDF, OWL, and SPARQL, advances in Machine Learning, Deep Learning, Natural Language Processing, and Information Retrieval has led to automated construction of knowledge graphs such as DBpedia, YAGO, Wikidata, Google’s and LinkedIn’s Knowledge Graph, Microsoft’s Satori, and Product Knowledge Graph from Amazon and eBay. Knowledge Graphs are used in several applications such as search, question answering, data integration, recommendation systems etc., across several domains such as healthcare, geosciences, manufacturing, aviation, power, oil and gas. There are several challenges related to knowledge graphs from the perspective of both the technology and its applications. This workshop aims to foster discussions along these perspectives.
Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities. However, an open challenge in this area is developing techniques that can go beyond simple edge prediction and handle more complex logical queries, which might involve multiple unobserved edges, entities, and variables. For instance, given an incomplete biological knowledge graph, we might want to predict "What drugs are likely to target proteins involved with both diseases X and Y?" -- a query that requires reasoning about all possible proteins that might interact with diseases X and Y.
In this talk we introduce a framework to efficiently make predictions about conjunctive logical queries -- a flexible but tractable subset of first-order logic -- on incomplete knowledge graphs. In our approach, we embed graph nodes in a low-dimensional space and represent logical operators as learned geometric operations (e.g., translation, rotation) in this embedding space. By performing logical operations within a low-dimensional embedding space, our approach achieves a time complexity that is linear in the number of query variables, compared to the exponential complexity required by a naive enumeration-based approach. We demonstrate the utility of this framework in two application studies on real-world datasets with millions of relations: predicting logical relationships in a network of drug-gene-disease interactions and in a graph-based representation of social interactions derived from a popular web forum.
Jure Leskovec is Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub. His research focuses on machine learning and data mining large social, information, and biological networks, their evolution, and the diffusion of information over them. Computation over massive data is at the heart of his research and has applications in computer science, social sciences, and biomedicine. This research has won several awards including a Lagrange Prize, Microsoft Research Faculty Fellowship, the Alfred P. Sloan Fellowship, and numerous best paper awards. Leskovec received his bachelor's degree in computer science from University of Ljubljana, Slovenia, and his PhD in in machine learning from the Carnegie Mellon University and postdoctoral training at Cornell University.
|9:00-9:30||Invited Talk: Denny Vrandecic, Google|
|9:30-10:00||Invited Talk: Jure Leskovec, Stanford|
1. Knowledge-Driven Stock Trend Prediction and Explanation via Temporal Convolution Network.
Shumin Deng, Ningyu Zhang, Wen Zhang, Jiaoyan Chen, Jeff Z. Pan and Huajun Chen
2. How new is the (RDF) news? Assessing knowledge graph completeness over news feed entities.
Tomer Sagi, Katja Hose and Yael Wolf
3. Content based News Recommendation via Shortest Entity Distance over Knowledge Graphs.
Kevin Joseph and Hui Jiang
4. Trust and Privacy in Knowledge Graphs.
Daniel Schwabe and Carlos Laufer
Computational Methods about Knowledge Graph
1. Jie Tang, Tsinghua University
2. Jure Leskovec, Stanford
3. Kuansan Wang, Microsoft Academic Search
4. Deborah McGuinness, RPI
5. Hassan Sawaf, Amazon
|1:30-2:00||Invited Talk: Benjamin Han, Microsoft|
|2:00-2:30||Invited Talk: Doug Raymond, Allen Institute for AI|
1. Building a Knowledge Graph for the Air Traffic Management Community
2. WebProtégé: A Cloud-Based Ontology Editor
Matthew Horridge, Rafael S Gonçalves, Csongor I Nyulas and Mark A Musen
3. Scalable Knowledge Graph construction over text using Deep Learning based Predicate Mapping
Aman Mehta, Aashay Singhal and Kamalakar Karlapalem
4. An Atention-based Model for Joint Extraction of Entities and Relations with Implicit Entity Features
Yan Zhou, Longtao Huang, Tao Guo, Songlin Hu and Jizhong Han
Knowledge Graph Industry Applications
1. Joshua Shinavier, Uber
2. Kim Branson, Genentech
3. Wei Zhang, Alibaba
4. Shima Dastgheib, NuMedii
5. Benjamin Han, Microsoft
6. Bogdan Arsintescu, LinkedIn
7. Fatma Özcan, IBM Almaden
8. Edgar Meij, Bloomberg
9. David Newman, Wells Fargo
Construction and Maintenance of Knowledge Graphs
Operations over Knowledge Graphs
Mining Knowledge Graphs
Storage mechanisms for Knowledge Graphs
Knowledge Graphs for NLP and IR
Knowledge Graphs in the industrial domain
Industry use cases and best practices
All papers submitted should have a maximum length of 8 pages and demo papers should be no more than 4 pages. All must be prepared using the ACM camera-ready template. Authors are required to submit their papers electronically in PDF format.
Soren Auer, Leibniz University of Hannover, Germany
Juan Sequeda, Capsenta, USA
Freddy Lecue, Accenture Technology Labs, Ireland
Steve Gustafson, Maana, USA
Craig Knoblock, University of Southern California, USA
Pascal Hitzler, Wright State University, USA
Tim Finin, University of Maryland, Baltimore County, USA
Axel Polleres, WU Vienna, Austria
Amelie Gyrard, Wright State University, USA
Pankesh Patel, Fraunhofer, USA
Peter Haase, metaphacts GmbH, Germany
Muhammad Intizar Ali, Insight Center, Ireland
Krzysztof Janowicz, UCSB, USA
Paul Groth, Elsevier Labs, Netherlands
Alibaba-Zhejiang University Frontier Tech Center (AZFT)