GraphNews

Concur. This is a great, detailed resource for those using #schema.org/Dataset https://t.co/j8H4ZUff2O pic.twitter.com/25KmdwOEJr— Aaron Bradley (@aaranged) December 8, 2020

Actually, this is pretty interesting > Ontology-based and User-focused Automatic Text Summarization (OATS): Using COVID-19 Risk Factors as an Example https://t.co/YvvevnKtbV pic.twitter.com/5njn4ZXeKj— Aaron Bradley (@aaranged) December 8, 2020

"To support the management of mappings throughout their entire lifecycle, we propose a comprehensive catalog of sophisticated mapping patterns that emerge when linking databases to ontologies." Mapping Patterns for Virtual Knowledge Graphs https://t.co/wTKGPIaPfT— Aaron Bradley (@aaranged) December 8, 2020

"How can we learn world models that endow agents with the ability to do temporally extended reasoning?" World Model as a Graph: Learning Latent Landmarks for Planning https://t.co/ifSa6j2uYJ pic.twitter.com/yWnuchuBI4— Aaron Bradley (@aaranged) December 8, 2020

A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources https://t.co/JsMcHN8Z6g pic.twitter.com/IxbRmK4ioo— Aaron Bradley (@aaranged) December 8, 2020

"... we argue that to date there are no effective solutions for supporting developers' decision-making process when deciding on an ontology reuse strategy" > The Landscape of Ontology Reuse Approaches @vale_carriero et al. https://t.co/LTqn85wv26 pic.twitter.com/AwjVPUDYk7— Aaron Bradley (@aaranged) December 8, 2020

"Hunters, busybodies, and the knowledge network building associated with curiosity": constructing networks of Wikipedia readers' exploration to capture differences in curiosity practice and information-seeking mechanisms.(Lydon-Staley et al, 2020)https://t.co/DVSuAB2jSQ pic.twitter.com/Jf9QtIkTsz— WikiResearch (@WikiResearch) December 8, 2020

Put your business rules in an EKG? No Y/N answer from @dmccreary but he sez "be aware of the fact that there are many benefits to treating your rules as data, making them searchable, making them reusable, and tracking rules execution in a knowledge graph." https://t.co/Uvlc5YBNuV— Aaron Bradley (@aaranged) December 9, 2020

Towards a Shared Peer-Review Taxonomy: An interview with Joris van Rossum and Lois Jones https://t.co/VQ0C807Rms pic.twitter.com/wGls0T8QKC— cbaumle (@cbaumle) December 10, 2020

"We present ten simple rules that support converting a legacy vocabulary - a list of terms available in a print-based glossary or table not accessible using web standards - into a FAIR vocabulary." https://t.co/5Jby0iXAXU pic.twitter.com/c2ovJjiAd5— Aaron Bradley (@aaranged) December 10, 2020

"https://t.co/u85cjjArgc’s primary focus is people—individuals who were enslaved, owned slaves, or participated in slave trading."Data curated in RDF, you can browse the resources and get RDF out of it. I could not find a SPARQL endpoint yet https://t.co/jwjDtYnhsD— Adrian Gschwend (@linkedktk) December 11, 2020

As requested , here are a few non-exhaustive resources I'd recommend for getting started with Graph Neural Nets (GNNs), depending on what flavour of learning suits you best. Covering blogs, talks, deep-dives, feeds, data, repositories, books and university courses! A thread 👇 pic.twitter.com/el1kb8rS4G— Petar Veličković (@PetarV_93) September 17, 2020

Background

It comes down to how easily the story falls apart.

We've made it even easier (and fun!) to explore the relationships between the millions of CC-licensed content sprawled across the web.

Ontotext and Synaptica join Forces with a Shared Product Roadmap to Speed up the Development of Enterprise Knowledge Graphs.

Upcoming at @emnlp2020:@danaikoutra and @tararootcake present CoDEx, a set of knowledge graph completion datasets extracted from @wikidata and @Wikipedia that improve upon existing knowledge graph completion benchmarks inscope & difficulty.https://t.co/YrZA4ac5GR— MichiganAI (@michigan_AI) November 13, 2020

Very, very cool:Using Neo4j with PySpark on Databricks https://t.co/CHKZTJSDXh#databricks #ApacheSpark #Neo4j pic.twitter.com/hcx69I6Hgx— Niels Berglund (@nielsberglund) November 18, 2020

From Knowledge Graphs to Knowledge Categories. @joshsh interviews Ryan Wisnesky of @ConexusAI for @TheGraphShow https://t.co/b1dxpdrBoh #knowledgegraphs #categorytheory #RDF #tinkerpop pic.twitter.com/wUpILFIV5z— Graph Day (@GraphDay) November 18, 2020

How can we gain maximum utility from a sophisticated ontology engineering such as #FIBO? @kptyson tells us how - by applying property paths combined w/ reasoning. Such techniques are useful for quality assuring large, complex ontologies & #knowledgegraphs. https://t.co/ZSfOVj5M1k— Ontotext (@ontotext) November 17, 2020

In this publication, Amazon scientists present the COVID-19 Knowledge Graph (CKG), a heterogeneous graph for extracting and visualizing complex relationships between COVID-19 scientific articles. Learn more: https://t.co/gmLEXJo48m #AmazonScience #COVID19 #KnowledgeGraphs pic.twitter.com/CzugJUhjs3— Amazon Science (@AmazonScience) November 16, 2020

What is common between BOMs and Graphs and why @openbom is using Neo4j https://t.co/xukMrCD1gE pic.twitter.com/oiwNPJwh1t— openbom (@openbom) November 20, 2020

"Ontology-driven Event Type Classification in Images" exploit structured information from #Wikidata to learn relevant event relations using deep neural networks. (Müller-Budack et al, 2020)https://t.co/fUFEN6wBqI@sherzodhakimov pic.twitter.com/CKyMMOKMaW— WikiResearch (@WikiResearch) November 19, 2020

Here's my first blog post for Amazon Neptune which discusses the new features it supports with its recent inclusion of @apachetinkerpop 3.4.8. #graphdb https://t.co/ImzR2rFIfX pic.twitter.com/EeHOR5k2xF— stephen mallette (@spmallette) November 18, 2020

Our chapter "#Ontology Extraction and Usage in the Scholarly Knowledge Domain" is now available in the book "Applications and Practices in Ontology Design, Extraction, and Reasoning". Using #MachineLearning to learn #KnowledgeGraphs of Science. Preprint: https://t.co/cWnnAihZUo https://t.co/gexnP0PSBq pic.twitter.com/bU363igotd— Francesco Osborne (@FraOsborne) November 23, 2020

These remarks cribbed from an talk that ended with the words "Launching the CCC Knowledge Graph", so another named enterprise knowledge graph coming our way soon, I guess. https://t.co/z9eIDO01yg— Aaron Bradley (@aaranged) November 23, 2020

"Fact-checking via Path Embedding and Aggregation", over Wikidata and DBPedia.(Pirro', 2020)https://t.co/opnd01It06 pic.twitter.com/b1IN7WomSA— WikiResearch (@WikiResearch) November 23, 2020

I say for some years that graph scaling is solved by throwing enough hardware at it and I'm VERY excited to hear we might even get dedicated "graph" hardware for it in the future! Great explanation! https://t.co/6XoAI3VOD2— Adrian Gschwend (@linkedktk) November 23, 2020

Leading enterprise #knowledgegraph provider @StardogHQ announces Stardog Cloud industry's first #cloud native offering enables organizations to transform enterprise data infrastructure into a comprehensive end-to-end #datafabric— Yuri Simione (@artika4biz) November 22, 2020