Data and Knowledge Group

― Knowledge Representation and Reasoning

Jiaoyan Chen

Senior Researcher

Biography

Dr. Jiaoyan Chen is a Senior Researcher at Department of Computer Science, University of Oxford and a member of Knowledge Representation and Reasoning Group, reporting to Prof. Ian Horrocks. He was previously a PostDoctoral Researcher in GIScience in Heidelberg University. Jiaoyan got his Ph.D in Computer Science and Technology in Zhejiang University, supervised by Prof. Zhaohui Wu and Prof. Huajun Chen. He was also a visiting student of Zurich University, supervised by Prof. Daning Hu. Jiaoyan got his Bachelor degree in Computer Science and Technology in Zhejiang University.

Research Interest

Knowledge Graph, Semantic Web, Neuro-Symbolic AI, Transfer and Zero-shot Learning

Ongoing Projects

Jiaoyan is now working on knowledge graph construction and curation with a combination of semantic reasoning and deep learning techniques, including 1) ontology embedding, 2) knowledge graph and ontology alignment, 3) semantic table annotation for knowledge construction; 4) knowledge graph refinement (e.g., correcting erroneous facts and formalism violations). The work is a part of “Artificial Intelligence for Data Analytics (AIDA)” project of the Alan Turing Institute and “Samsung Knowledge Graph Construction for Personalisation” project funded by Samsung Research UK. Jiaoyan is also involved in the data science program of SIRIUS in Oslo University (with Ernesto Jiménez-Ruiz, Erik B. Myklebus, etc.), and in cooperation with the NLP and KG group of Tencent Jarvis Lab.

The knowledge graph construction and curation projects involve new Neuro-Symbolic technqies for challenges such as the sample shortage and the subsymbolic representtion of logics. Jiaoyan has been working on relevant techniques including OWL ontology embedding, knowledge augmented zero-shot (transfer) learning and machine learning explanation. External cooperators include Huajun Chen and Yuxia Geng from Zhejiang University, Jeff Z. Pan from The University of Edinburgh and so on.

Recent Activities

Selective Publications

  • Jiaoyan Chen, Yuxia Geng, Zhuo Chen, Ian Horrocks, Jeff Z. Pan and Huajun Chen. "Knowledge-aware Zero-shot Learning: Survey and Perspective". IJCAI Survey Track (accepted), 2021. Paper
  • Jiaoyan Chen, Pan Hu, Ernesto Jimenez-Ruiz, Ole Magnus Holter, Denvar Antonyrajah and Ian Horrocks. "OWL2Vec*: Embedding of OWL Ontologies". Machine Learning, Springer, 2021 (accepted). Github,Paper
  • Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yuejia Xiang, Ningyu Zhang, Yefeng Zheng. "Unsupervised Knowledge Graph Alignment by Probabilistic Reasoning and Semantic Embedding". IJCAI, 2021 (accepted).
  • Yuejia Xiang, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Zhenxi Lin and Yefeng Zheng. "OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding". Findings of ACL, 2021 (accepted).
  • Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Xi Chen and Erik B. Myklebust. "Correcting Assertions and Alignments of Large Scale Knowledge Bases", 2021, submitted to SWJ. Pre-print
  • Jiaoyan Chen, Ernesto Jimenez-Ruiz, Ian Horrocks, Denvar Antonyrajah, Ali Hadian and Jaehun Lee. "Augmenting Ontology Alignment by SemanticEmbedding and Distant Supervision". ESWC, 2021. Github/Paper
  • Yuxia Geng, Jiaoyan Chen, Zhuo Chen, Jeff Z. Pan, etc. "OntoZSL: Ontology-enhanced Zero-shot Learning". The Web Conference (WWW), 2021 (accepted). With case studies on both image classification and KG link prediction.Paper,Data and Codes
  • Jiaoyan Chen, Freddy Lecue, Jeff Z. Pan, Shumin Deng, Huajun Chen. "Knowledge Graph Embeddings for Dealing with Concept Drift in Machine Learning". Journal of Web Semantics, 2021. Paper
  • Ian Horrocks, Jiaoyan Chen and Jaehun Lee. "Tool Support for Ontology Design and Quality Assurance". ICBO 2020 Integrated Food Ontology Workshop (IFOW). Paper
  • Ziheng Zhang, Jiaoyan Chen, Xi Chen, Hualuo Liu, Yuejia Xiang, Bo Liu and Yefeng Zhang. "An Industry Evaluation of Embedding-based Entity Alignment". The 28th International Conference on Computational Linguistics (COLING'2020), Industry Track. Data,Paper,Video
  • Jiaoyan Chen, Freddy Lecue, Yuxia Geng, Jeff Z. Pan and Huajun Chen. "Ontology-guided Semantic Composition for Zero-Shot Learning", KR 2020 -- Special Session KR and Machine Learning Paper,Video
  • Yuxia Geng, Jiaoyan Chen, Zhiquan Ye, Wei Zhang and Huajun Chen. "Explainable Zero-shot Learning via Attentive Graph Convolutional Network and Knowledge Graphs" Semantic Web Journal. Paper
  • Ernesto Jiménez-Ruiz, Oktie Hassanzadeh, Vasilis Efthymiou, Jiaoyan Chen and Kavitha Srinivas. "SemTab 2019: Resources to Benchmark Tabular Data to Knowledge Graph Matching Systems." ESWC 2020. Paper
  • Jiaoyan Chen, Xi Chen, Ian Horrocks, Ernesto Jiménez-Ruiz and Erik B. Myklebus. "Correcting Knowledge Base Assertions." The Web Conference (WWW) 2020. Paper Github
  • Ernesto Jimenez-Ruiz, Asan Agibetov, Jiaoyan Chen, Matthias Samwald and Valerie Cross. "Dividing the Ontology Alignment Task with Semantic Embeddings and Logic-based Modules." the 24th European Conference on Artificial Intelligence (ECAI) 2020.
  • Jiaoyan Chen, Ernesto Jiménez-Ruiz and Ian Horrocks. "Canonicalizing Knowledge Base Literals." International Semantic Web Conference (ISWC) 2019. Paper Github
  • Erik B. Myklebust, Ernesto Jiménez-Ruiz, Jiaoyan Chen, Raoul Wolf, Knut Erik Tollefsen. "Knowledge Graph Embedding for Ecotoxicological Effect Prediction." International Semantic Web Conference (ISWC) 2019. In-Use Track Best Student Paper
  • Jiaoyan Chen, Ernesto Jiménez-Ruiz, Ian Horrocks, and Charles Sutton. "Learning Semantic Annotations for Tabular Data." IJCAI 2019. Github Paper
  • Jiaoyan Chen, Ernesto Jiménez-Ruiz, Ian Horrocks, and Charles Sutton. "ColNet: Embedding the Semantics of Web Tables for Column Type Prediction." AAAI 2019. Github
  • Jiaoyan Chen, Freddy Lécué, Jeff Z. Pan, Ian Horrocks, and Huajun Chen. "Knowledge-based Transfer Learning Explanation." KR 2018. Paper
  • Jiaoyan Chen, Yan Zhou, Alexander Zipf and Hongchao Fan. "Deep Learning from Multiple Crowds: A Case Study of Humanitarian Mapping." IEEE Transactions on Geoscience and Remote Sensing 57 (3), 1713-1722. (Project DeepVGI in University of Heidelberg, see more)
  • Jiaoyan Chen, Freddy Lécué, Jeff Z. Pan, and Huajun Chen. "Learning from ontology streams with semantic concept drift." IJCAI 2017. Paper
  • Jiaoyan Chen, Huajun Chen, Zhaohui Wu, Daning Hu, and Jeff Z. Pan. "Forecasting smog-related health hazard based on social media and physical sensor." Information Systems 64 (2017): 281-291.
  • Jiaoyan Chen, Shumin Deng and Huajun Chen. "CrowdGeoKG: Crowdsourced Geo-Knowledge Graph." China Conference on Knowledge Graph and Semantic Computing (CCKS) 2017.

See the complete paper list.

Invited Talks

  • "Knowledge Graph Curation with Deep Learning and Semantic Reasoning". Tencent Technology, Shenzhen, China, 24/10/2019. Slide
  • "Knowledge Graph Curation with Deep Learning and Semantic Reasoning". Southern University of Science and Technology, Shenzhen, China, 23/10/2019.
  • "Knowledge Graph Curation with Deep Learning". Southeast University, Nanjing, China, 23/08/2019

Name

Jiaoyan Chen

Posts

Senior Researcher

Projects

Sirius,AIDA,Samsung

Contact Information

Room 306, Wolfson Building, Parks Road, Oxford OX1 3QD

email: firstname.lastname@cs.ox.ac.uk

Twitter: @ChenJiaoyan1

News

New Positions!

The KRR group has new postdoctoral positions available! Research topic includes Ontology, Knowledge Graph, Semantic Web, Logics, as well as the interdisciplinary between them and machine learning. Send your CV to Ian or Bernardo. [added on 26/11/2019]

In-Use Track Best Student Paper in ISWC'19>

The paper "Knowledge Graph Embedding for Ecotoxicological Effect Prediction" gets In-Use Track Best Student Paper in ISWC'19. The work was done when the first student author Erik B. Myklebust was visiting the KRR group, with Jiaoyan Chen.

3 Paper accepted in AAAI'18

Three papers co-authored by the KRR group have been accepted in AAAI'18:
- "Stream Reasoning in Temporal Datalog" by A. Ronca, M. Kaminski, B. Cuenca Grau, B. Motik, and I. Horrocks;
- "Optimised Maintenance of Datalog Materialisations" by P. Hu, B. Motik, and I. Horrocks; and
- "Goal-Driven Query Answering for Existential Rules with Equality" by M. Benedikt, B. Motik, and E. Tsamoura.

Professor Ian Horrocks is a new honorary doctorate at University of Oslo, Faculty of Mathematics and Natural Sciences

Professor Ian Horrocks received an honorary doctorate from the University of Oslo.

Best paper award at IJCAI'17

The paper entitled "Foundations of Declarative Data Analysis Using Limit Datalog Programs" and authored by M. Kaminski, B. Cuenca Grau, B. Motik, E. V. Kostylev, and I. Horrocks received the best paper award at the 26th International Joint Conference on Artificial Intelligence (IJCAI'17).

3 papers accepted in IJCAI'17

Three papers co-authored by the KRR group have been accepted in IJCAI'17:
- "Query Reformulation: Theory and Practice" by M. Benedikt, E. V. Kostylev, F. Mogavero, and E. Tsamoura;
- "Foundations of Declarative Data Analysis Using Limit Datalog Programs" by M. Kaminski, B. Cuenca Grau, B. Motik, E. V. Kostylev, and I. Horrocks; and
- "The Bag Semantics of Ontology-Based Data Access" by C. Nikolaou, E. V. Kostylev, G. Konstantinidis, M. Kaminski, B. Cuenca Grau, and I. Horrocks.

Paper accepted in PODS'17

The paper entitled "Benchmarking the chase" authored by Michael Benedikt, George Konstantinidis, Giansalvatore Mecca, Boris Motik, Paolo Papotti, Donatello Santoro, and Efthymia Tsamoura has been accepted in PODS'17.

Andrew Bate defends his PhD Thesis

Andrew Bate has successfully defended his PhD Thesis on Consequence Based Reasoning. Congratulations to Dr. Andrew Bate!

Best applications paper award at ISWC'16

Our paper entitled "Semantic Technologies for Data Analysis in Health Care" received the Best Applications Paper Award at the International Semantic Web Conference (ISWC 2016).

4 papers accepted in ISWC'16

Four papers authored by the KRR group have been accepted in the International Semantic Web Conference (ISWC 2016).

Best paper award at ICDT'16

Mark Kaminski and Egor Kostylev received the best paper award at ICDT 2016 for their paper entitled "Beyond Well-Designed SPARQL".