GraphNews

AutoML on graphs is a thing. In the paper Automated Machine Learning on Graphs: A Survey (https://lnkd.in/djs25FfM), the authors present a comprehensive...

New Video! Zhaocheng Zhu explains his paper NeurIPS'21 paper "Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction...

Artificial Intelligence has a long history of oscillating between two somewhat contradictory poles. On one side, exemplified by Noam Chomsky, Marvin Minsky, Seymour Papert, and many others, is the idea that cognitive intelligence was algorithmic in nature – that there were a set of fundamental precepts that formed the foundation of language, and by extension,… Read More »Where Semantics and Machine Learning Converge

Very honored to receive the ELLIS PhD Award for my thesis on Deep Learning with Graph-Structured Representations -- alongside with with @NagraniArsha for her work on multimodal DL (congrats!) https://t.co/FUzNA87okN pic.twitter.com/W2KrbQN7yS— Thomas Kipf (@thomaskipf) December 9, 2021

In 2021, knowledge graphs weren't just blossoming-they were blooming-and it was clear that we are now in the knowledge graph stage of KM development

Enterprise Knowledge Graph Platform ROI: Providing readers with a framework to evaluate the potential financial impact of deploying Stardog on their own organizations.

Maya Natarajan, senior director of product marketing at Neo4j, explores the value of knowledge graphs for CIOs

For this blog, Ahren Lehnert, explores knowledge graphs and their punk rhizomatics. A paradigm shift in knowledge organization and sharing.

Interested in using Wikidata & Wiktionary to extract lexicographical information?@sina_ahm created a simple SPARQL query generator that helps non-experts get familiar w/ #SPARQL & create queries to look up words in @wikidata & #Dbnary:👉 https://t.co/gS6JG8EIFb#NLProc pic.twitter.com/9UOCABh3c9— ELEXIS EU (@elexis_eu) December 1, 2021

Curious about the most used ontologies in the agri-food domain? Our #Ontologies Community of Practice has developed a webpage featuring the most popular ontologies & info on those developed by @CGIAR and partners.Find it here: https://t.co/AMVeSHCpdi pic.twitter.com/LmazTo4V2T— CGIAR Platform for Big Data in Agriculture (@CGIAR_Data) December 9, 2021

"... most Entity Linking approaches use Wikidata in the same way as any other knowledge graph missing the chance to leverage Wikidata-specific characteristics to increase quality" > Survey on English Entity Linking on Wikidata https://t.co/JYHJMfVHsO pic.twitter.com/hRxRp3nhnQ— Aaron Bradley (@aaranged) December 10, 2021

Using custom Named Entity Recognition and Relation Extraction models

Anti-Money Laundering Alert Optimization Using Machine Learning with Graphs https://t.co/e7fQg57Mrt pic.twitter.com/8nZ7QzeUD5— Aaron Bradley (@aaranged) December 15, 2021

ISEEQ: Information Seeking Question Generation using Dynamic Meta-Information Retrieval and Knowledge Graphs @manasgaur90 et al. https://t.co/Gg6s7J0kwH pic.twitter.com/kNbaji06Vf— Aaron Bradley (@aaranged) December 15, 2021

A Simple Standard for Sharing Ontological Mappings (SSSOM) @NicoMatentzoglu + ~40 others https://t.co/rCAyGakxdY pic.twitter.com/GK0fzPFx6q— Aaron Bradley (@aaranged) December 15, 2021

What if we model a graph as a set of subgraphs instead of a set of interconnected nodes? Hint: expressive power + equivariance! 🧵Joint work by a super team: @beabevi_ * @dereklim_lzh * @balasrini32 @ChenCaiUCSD @gblearning42 @mmbronstein @HaggaiMaronhttps://t.co/6rW4e47RhN pic.twitter.com/Ajl8L5xdDc— Fabrizio Frasca (@ffabffrasca) December 15, 2021

MedGraph: An experimental semantic information retrieval method using knowledge graph embedding for the biomedical citations indexed in PubMed https://t.co/B3tmoVilDt pic.twitter.com/DvEVoU53ec— Aaron Bradley (@aaranged) December 14, 2021

TempoQR: Temporal Question Reasoning over Knowledge Graphs https://t.co/6SXVnzyG1x pic.twitter.com/LXQW2XYbUb— Aaron Bradley (@aaranged) December 14, 2021

Predictive UX explores UX Design for Enterprise Search Using Knowledge Graphs

Graph-based hierarchical record clustering for unsupervised entity resolution https://t.co/I0saMXcQFL pic.twitter.com/eB7Cphflp3— Aaron Bradley (@aaranged) December 14, 2021

Use our SPARQL micro-services to query #PubMedCentral with #SPARQL using a PMID or PMCID, and get article metadata in #RDF.https://t.co/1RKvb9GZkvhttps://t.co/XxjTUy2Gut@pubmed @wimmics @Inria @uca_research @Laboratoire_I3S #ScientificLitterature pic.twitter.com/bm8OdpzoaN— Michel Franck (@franck_michel2) December 7, 2021

Check out how knowledge graphs have transformed the supply chain industry in the continued wake of the pandemic.

Embedding knowledge on ontology into the corpus by topic to improve the performance of deep learning methods in sentiment analysis - Scientific Reports https://t.co/W0lKPRCh84 #DL #AI #ML #DeepLearning #ArtificialIntelligence #MachineLearning #ComputerVision #AutonomousVehicles— Deep_In_Depth (@Deep_In_Depth) December 11, 2021

The long-awaited major release of Bloom 2.0 has arrived with some key feature updates we think you’ll find helpful in your data exploration.

UFO: Unified Foundational Ontology / Giancarlo Guizzardi et al. https://t.co/GuTFxstIqV pic.twitter.com/9BJG1GUdIt— Aaron Bradley (@aaranged) December 16, 2021

Manufacturing Line, Wikimedia Commons, 2014 Fakery certainly isn’t limited to news and social media. The Organisation for Economic Co-operation and Developmen…

Over the last 20 years my life revolved around doing “everything modeling” - building models, discussing modeling, teaching modeling and so on. Unsurprisingly, I have an opinion about models and modeling.

In the previous article on how data modeling is different today, I talked about modularity and expressivity required for defining shared models. Such concepts are often talked about in abstract terms.

To combat antibiotic resistance, Roland Haas uses a knowledge graph to offer patients the right antibiotic for the right diagnosis at the right dosage.

How knowledge graphs model the relationships within scientific data in an open and machine-understandable format for better science.