Knowledge Graphs and E-commerce

August 24: 8 AM- 12 PM PDT

Held virtually in conjunction with KDD’20

Knowledge Graphs (KGs) have become immensely popular in recent years, both in industry and academia. Although graphs have been ubiquitous in AI and knowledge discovery since the earliest days, the Google Knowledge Graph led to the realization that representing ‘knowledge’ by way of sets of triples, often automatically extracted from raw data, could be used to power rich applications like knowledge panels and semantic search. Academic and industrial interest in the subject flourished soon after, with research published across topics as diverse as Entity Resolution and knowledge graph embeddings (primarily in venues like NIPS, AAAI and KDD), to representation and reasoning over knowledge graphs (primarily in venues like VLDB and ISWC). More recently, with the rapid rise and ongoing growth of e-commerce, there has been growing interest from major retailers and e-commerce players alike, including Walmart, Amazon and Home Depot, to adopt knowledge graphs (or an analogous graph-based technology like Amazon’s Product Graph) for facilitating rich machine learning and e-commerce applications. This workshop will cover knowledge discovery and knowledge graphs, including construction, application and embeddings, primarily for e-commerce and enterprise applications.

Key Dates

April 10: First call for papers
April 15: Submissions open
June 15: Workshop papers due
July 15: Notification of accepted papers
August 2: Release of final workshop schedule
Aug. 24: Workshop (Half-Day)

Confirmed Keynote Speakers and Panelists

Audience and Format

This workshop welcomes submissions from both researchers and industry practitioners in knowledge graphs (KG) and e-commerce, and KG applications, with a particular emphasis on real-world deployment and pipelines that are relevant to industrial settings. We solicit research that is broadly related to e-commerce KG research and sub-fields, including data cleaning (e.g., Entity Resolution), representation learning and embeddings, natural language processing (e.g., information extraction) and information retrieval (e.g., semantic search). Full paper submissions (maximum 8 pages) are solicited in the form of research papers which propose new techniques and advances with industrial potential using data mining techniques for KGs, as well as papers from industry that describe practical applications and system innovations in e-commerce application areas. Short papers (maximum 4 pages) describing case studies or work-in-progress are also solicited. Exceptionally well-argued position papers are also welcome.

Call For Papers

In addition to short and long papers (see below), we also solicit extended abstracts (1-2 pages) covering topical areas of research (either in knowledge graphs, e-commerce or both) that are appropriate for the workshop. Authors of selected abstracts will be invited for oral presentations.

Short and long papers are solicited for the following set of non-exhaustive topics:

Theory, Algorithms and Methods:

•Knowledge graph construction e.g., constructing KGs from structured, semi-structured and natural language data
• Novel definitions and theories regarding KGs , especially taking into account attributes and features commonly found in enterprise settings, including customers, products and spatiotemporal dependencies in KGs.
•Querying and infrastructure of KG-centric architectures and applications
•Effective use of public KGs
•Foundational proposals for content models that combine statistical and symbolic representations
•Novel embedding algorithms , especially for large-scale KGs
•Statistical learning methods and algorithms for working with noisy KGs
•Data quality assessment for large-scale enterprise KGs


• Web search
• Question answering
• Personalization
• Data Mining
• User interfaces and visualization
•Semantic recommendations
•Link prediction
•Node classification
•Instance matching/Entity resolution
•Knowledge graph embeddings
• Knowledge graph completion

Experiments, Systems and Data

•Novel datasets , especially datasets acquired through, or useful for evaluating, hybrid KG construction approaches utilizing a combination of structured, semi-structured and natural language data
•Novel methodologies , concerning both evaluations and data curation/collection
•Experimental results using existing methods, including negative results of interest
•Systems issues in KG-centric systems , including best practices, case studies, lessons learned, and feature descriptions

Vision, Opinion and Position Papers

We will also accept a small number of vision, opinion and position papers that provide discussions on challenges and roadmaps (for KG-centric systems, applications and emerging models for e-commerce and product data).

Submission Directions

Submissions are limited to a total of eight (8) pages, including all content and references, and must be in PDF format and formatted according to the new Standard ACM Conference Proceedings Template. For LaTeX users: unzip, make, and use sample-sigconf.tex as a template.

Additional information about formatting and style files is available online at:

Papers that do not meet the formatting requirements will be rejected without review. The accepted papers will be published online and will not be considered archival. Select papers may be invited to a special journal issue on e-commerce and knowledge graphs. Proceedings will be available for download after the conference.

We are using the EasyChair system for submissions. Please submit your paper using this link:

Please email any enquiries to

Accepted Papers

**Links to paper PDFs will be available starting August 1, 2020**

Active Learning for Product Type Ontology Enhancement in E-commerce. Yun Zhu, Sayyed Zahiri, Jiaqi Wang, Han-Yu Chen and Faizan Javed. [Paper]

Knowledge Graphs and the Dialogic Potential of the Web. Teodora Petkova. [Paper]

Transfer Learning on User Behaviors for Multi-lingual eCommerce Systems. Wei-Lun Su, Pei-Ling Chen, Chia-Chuan Ho and Tzu-Chiang Liou. [Paper]

Using Machine Teaching in Text Analysis: Case Study on Using Machine Teaching with Knowledge Graphs. Thomas Cook, Rajib Saha, Steven Sarsfield and Sandip Bhaumik. [Paper]

An Interactive Scribe for Guiding Task-Oriented Conversations in Enterprise Call Centers. Devin Conathan, Joe Bockhorst, Dan Dickinson, Shailesh Acharya, Glenn Fung and Scott Rouse. [Paper]

Human in the Loop Enrichment of Product Graphs with Probabilistic Soft Logic. Marouene Sfar Gandoura, Zografoula Vagena and Nikolaos Vasiloglou. [Paper]

On using Product-Specific from Web Data Commons: An Empirical Set of Best Practices. Ravi Kiran Selvam and Mayank Kejriwal. [Paper]


All times below are August 24, 2020 Pacific Time.



  • Mayank Kejriwal
    University of Southern California
  • Qi He
  • Faizan Javed
    The Home Depot
  • Anoop Kumar
  • Andrey Kan

Program Committee

  • Mike Dillinger, AMTA
  • Surya Kallumadi, The Home Depot
  • Subhabrata Mukherjee, Microsoft
  • Michael Spranger, Sony Computer Science Laboratories Inc.
  • Nikolaos Vasiloglou, Relational AI
  • Jaewon Yang, LinkedIn
  • Ganapathy Mani, Purdue University