GraphNews

In the last couple of months, I’ve been noticing a gradual shift in the kind of articles that we receive at Data Science Central. We still get a fair amount of data science content, but increasingly (and admittedly with a bit of encouragement) we’re seeing more articles centered around graphs and semantics. I don’t believe… Read More »DSC Weekly Digest 22 February 2022: Graphology

You’ve probably seen web editors based on the idea of blocks. I’m typing this in WordPress, which has a little + button that brings up a long list of potential blocks that you can inser…

Can Machine Learning Do Symbolic Manipulation?  I spent some time over the holidays engaged in a fascinating online conversation. The gist of it was a variation of an argument that has been going on in the realm of artificial intelligence from the time of Minsky and Seymour Papert: Whether it is possible for neural networks to… Read More »DSC Weekly Digest 04 Jan 2022: Can Machine Learning Do Symbolic Manipulation?

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

Anti-Money Laundering Alert Optimization Using Machine Learning with Graphs https://t.co/e7fQg57Mrt pic.twitter.com/8nZ7QzeUD5— 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

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

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

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

Excited to share a Colab tutorial on graph neural networks with the JAX+Jraph stack, which we use in-house at DeepMind! Developed by Lisa Wang and Nikola... 12 comments on LinkedIn

"The Open Application Group (OAGi) and the Industrial Ontologies Foundry (IOF) have signed an agreement to produce industrial ontologies." [PR] https://t.co/zz511UBuYE— Aaron Bradley (@aaranged) March 3, 2021

Identifying Ingredient Substitutions Using a Knowledge Graph of Food https://t.co/5pZWc9Bt94 pic.twitter.com/PgkMr9idHj— Aaron Bradley (@aaranged) March 3, 2021

Last week Google added Graph Neural Network support to TensorFlow. This comes in the wake of PyTorch Geometric getting a lot of support from Meta (formerly...

G.V() is an all-in-one Gremlin IDE to write, test and analyze results for your TinkerPop-enabled graph database - in open beta now and looking for feedback: https://t.co/0FLK7kC9K9 #graphdb pic.twitter.com/7U8PeKFsm9— TinkerPop (@apachetinkerpop) November 22, 2021

How to tune the hyperparameters of FastRP to your specific problem

Papers With Code highlights trending Machine Learning research and the code to implement it.

Classical event logs have the fundamental shortcoming of describing process behavior only in isolated process executions from the viewpoint of a single case entity. Most real-life processes involve…

Excited to share our collaboration with @GoogleAI: SMORE is a scalable knowledge graph completion and multi-hop reasoning system that scales to hundreds of millions of entities and relations. @ren_hongyu, @hanjundai, et al.https://t.co/O2xM9iYMjihttps://t.co/BImVmbZAFi pic.twitter.com/H52aFOejkv— Jure Leskovec (@jure) November 1, 2021

This week’s publication of the Pandora Papers--which the International Consortium of International Journalists based on a trove of private data leaked

While many of the programming libraries encapsulate the inner working details of graph and other algorithms, as a data scientist it helps a lot having a reason…

Distribution Knowledge Embedding for Graph Pooling https://t.co/YsQBXwbFtZ pic.twitter.com/ZXbpOKDrLC— Aaron Bradley (@aaranged) September 30, 2021

Super nice talk by @matej_zecevic on #Neuro-#Causality and our integration of graph neural networks and structural causal models. 🎞️👉 https://t.co/S2XNuOqZ61 🙏 to @JackccLu for inviting Matej! pic.twitter.com/jamZ20WoGt— Kristian Kersting (@kerstingAIML) September 28, 2021

Breadcrumbs is a blockchain analytics platform accessible to everyone. It offers a range of tools for investigating, monitoring, tracking, and sharing r...

Open Source Tool - Cybersecurity Graph Database in Neo4j - GitHub - amberzovitis/GraphKer: Open Source Tool - Cybersecurity Graph Database in Neo4j

"SYGMA: System for Generalizable Modular Question Answering Over Knowledge Bases", tested on #DBPedia and #Wikidata + a new Temporal QA benchmarkdataset based on Wikidata.(Neelam et al, 2021)data: https://t.co/0tkY9sjA9Zpaper: https://t.co/rZDw4bW56Q pic.twitter.com/XqFwp2def2— WikiResearch (@WikiResearch) October 6, 2021

Our paper titled "A Survey of #RDF Stores & #SPARQL Engines for Querying Knowledge Graphs" has been accepted to #VLDB Journal. A survey of over 120 RDF stores and #KnowledgeGraphs. https://t.co/SsFroOOBI5 @aidhog @NgongaAxel @akswgroup @DiceResearch pic.twitter.com/o4fiwG1VJq— Muhammad Saleem (@saleem_muhamad) October 3, 2021

Program Transfer and Ontology Awareness for Semantic Parsing in KBQA [Knowledge Base Question Answering] https://t.co/4UHsmhhkRz pic.twitter.com/iTyYwse9Jf— Aaron Bradley (@aaranged) October 13, 2021

"No Need to Know Everything! Efficiently Augmenting Language Models With External Knowledge" Instead of packing all knowledge in the model, the system provides external Wiki knowledge and trains the model to use that source.(Kaur et al 2021)https://t.co/U3VcZn0XyY@sbhatia_ pic.twitter.com/XNPZj5Neys— WikiResearch (@WikiResearch) October 15, 2021

Knowledge Graph-enhanced Sampling for Conversational Recommender System https://t.co/LfD8ixZT7K pic.twitter.com/H5HFPYsAXN— Aaron Bradley (@aaranged) October 14, 2021