In Search for a Cure: Recommendation With Knowledge Graph on CORD-19

  title={In Search for a Cure: Recommendation With Knowledge Graph on CORD-19},
  author={Iris Shen and Le Zhang and Jianxun Lian and Chieh-Han Wu and Miguel Gonz{\'a}lez-Fierro and Andreas Argyriou and Tao Wu},
  journal={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
  • Iris Shen, Le Zhang, +4 authors Tao Wu
  • Published 23 August 2020
  • Computer Science
  • Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
The whole globe has cranked up for coping with the COVID-19 situation. The hands-on tutorial targets at providing a comprehensive and pragmatic end-to-end walk-through for building an academic research paper recommender for the use case of COVID-19 related study, with the help of knowledge graph technology. The code examples that demonstrate the theories are reproducible and can hopefully provide value for researchers to build tools that support conducting research to find a cure to COVID-19. 
2 Citations
COBERT: COVID-19 Question Answering System Using BERT
COBERT is proposed: a retriever-reader dual algorithmic system that answers the complex queries by searching a document of 59K corona virus-related literature made accessible through the Coronavirus Open Research Dataset Challenge (CORD-19).
Learning with joint cross-document information via multi-task learning for named entity recognition
This work presents a cross-document NER model that builds internal relationships for each token among all its multiple occurrences in different documents and achieves better results than the sentence-level and document-level NER models.


Microsoft Academic Graph: When experts are not enough
The design, schema, and technical and business motivations behind MAG are described and how MAG can be used in analytics, search, and recommendation scenarios are elaborated.
Inductive Representation Learning on Large Graphs
GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
Microsoft Recommenders: Best Practices for Production-Ready Recommendation Systems
This work presents Microsoft Recommenders, an open-source Github repository for helping researchers, developers and non-experts in general to prototype, experiment with and bring to production both classic and state-of-the-art recommendation algorithms.
DKN: Deep Knowledge-Aware Network for News Recommendation
A deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation and achieves substantial gains over state-of-the-art deep recommendation models is proposed.
Representation Learning on Networks: Theories, Algorithms, and Applications
This tutorial aims to provide the audience with the underlying theories in network representation learning, as well as the experience in translating this line of research into real-world applications on the Web.
DeepWalk: online learning of social representations
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.
A Review of Microsoft Academic Services for Science of Science Studies
The use of three key AI technologies that underlies its prowess in capturing scholarly communications with adequate quality and broad coverage are focused on, including a reinforcement learning approach to assessing scholarly importance for entities participating in scholarly communications, called the saliency, that serves both as an analytic and a predictive metric in MAS.
  • 2020
CORD-19 Data set
  • 2020
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
This work proposes a new model named LightGCN, including only the most essential component in GCN -- neighborhood aggregation -- for collaborative filtering, and is much easier to implement and train, exhibiting substantial improvements over Neural Graph Collaborative Filtering (NGCF) under exactly the same experimental setting.