Lmst

Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction
https://2024.eswc-conferences.org/wp-content/uploads/2024/04/146640020.pdf

#knowledgeGraph #syntheticData #neuroSymbolicAI #ArtificialIntelligence #semanticWeb #linkPrediction #graphEmbedding

PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips https://2024.eswc-conferences.org/wp-content/uploads/2024/04/146640336-1.pdf

#knowledgeGraph #syntheticData #neuroSymbolicAI #ArtificialIntelligence #semanticWeb #linkPrediction #graphEmbedding

Very glad to announce that we got 2 best paper awards at #ESWC2024 for our works about PyGraft (resource track) and semantically enhanced loss functions to learn graph #embedding (research track)! Congratulations Nicolas Hubert!

#knowledgeGraph #syntheticData #neuroSymbolicAI #ArtificialIntelligence #semanticWeb #linkPrediction #graphEmbedding

Very happy to announce our new paper accepted in @eswc_conf
#ESWC2024: "Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction"!

📎 https://arxiv.org/pdf/2303.00286.pdf

w/ N. Hubert, A. Brun, and D. Monticolo

#knowledgeGraph #semanticWeb #machineLearning #linkPrediction #neurosymbolicAI #artificialIntelligence #linkedOpenData #graphEmbeddings #embeddings #graphNeuralNetworks

Our paper "PyGraft: Configurable Generation of Synthetic #Schemas and #KnowledgeGraphs at Your Fingertips" has been accepted in @eswc_conf #ESWC2024!

Paper: https://arxiv.org/pdf/2309.03685.pdf
Code: https://github.com/nicolas-hbt/pygraft

PyGraft is a configurable #Python tool to generate both synthetic #schemas and #knowledgeGraphs easily, supporting several RDFS and OWL constructs. These #datasets are useful for, e.g., #neurosymbolicAI, #linkPrediction, #nodeClassification, #nodeClustering, #ontology repairing

2nd add on to our free MOOC lecture series on #KnowledgeGraphs is a colab notebook on knowledge graph completion with TransE through which my colleagues Ann Tan and @MahsaVafaie will guide you in the video.
#OpenHPI video: https://open.hpi.de/courses/knowledgegraphs2023/items/48Sn5Tr9RKo24RXu7OwgOz
youtube video: https://www.youtube.com/watch?v=IVTVzgCbHOw&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=67
colab notebook: https://colab.research.google.com/drive/104ad-kusmzfYgkK_L8ETWUAjfdreE9e2#scrollTo=fQ08XPbaZgQ4

@fizise @fiz_karlsruhe #semanticweb #kge #embeddings #linkprediction #videolecture #video

From the colab notebook of our 2nd add on to the free OpenHPI MOOC course Knowledge Graphs - Foundations and Applications. The graphics depicts a TSNE mapping of knowledge graph embeddings for the Game of Thrones characters.

Knowledge Graph Embeddings (KGEs) are a very useful tool for few- and zero-shot learning. Of course Link Prediction and #KnowledgeGraph Completion are the most prominent tasks for KGEs. My colleague Ann Tan and I will start our investigation of KGEs in this section of our free #kg2023 lecture.
OpenHPI video: https://open.hpi.de/courses/knowledgegraphs2023/items/3xfeKrryLMeY45OXSwBd86
youtube video: https://www.youtube.com/watch?v=UGmtYSCXsQk&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=62
slides: https://zenodo.org/records/10185280
@tabea @sashabruns @MahsaVafaie @fiz_karlsruhe @fizise #embeddings #linkprediction

Still from the OpenHPI MOOC lecture video "Knowledge GRaphs - Foundations and Applications", Week 6: Intelligent Applications with Knowledge Graphs and Deep LEarning, 6.2, Knowledge GRaph Embeddings. The slide shows "Inductive Link Prediction", i.e. predict a different knowledge graph that is not given with the training data.

PyGraft will help you generate new and tailored benchmark KG #datasets useful in various fields including but not limited to #neurosymbolicAI, #linkPrediction, #nodeClassification, #nodeClustering, #ontology repairing, pattern mining, reasoning, scalability studies, etc.

Feel free to download, star, fork, share and tell us about any usage you foresee! We welcome all contributions or ideas to improve PyGraft! Looking forward to feedback from #semanticWeb #machineLearning and other communities!

As a 2nd topic of this last #ise2023 lecture, we were discussing #KnowledgeGraph Completion. Most simple approach for unsupervised #linkprediction based on (here translation-based) knowledge graph embeddings was explained on the example of Isaac Asimov.
Slides: https://drive.google.com/file/d/1atNvMYNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link
@fizise @enorouzi #scifi #knowledgegraphs #ai #deeplearning #embeddings

Slide from the last Information Service Engineering 2023 lecture, ISE Applications, 5.2 Knowledge Graph Completion:
Link Prediction with KG Embeddings
- Use Translational Embeddings
-- Unsupervised methods, e.g. TransE, use zs + zp to predict zo
-- Supervised Methods for prediction, based on embedding vectors

Vectors for "Isaac Asimov" and "occupation" are added. For the resulting vector a nearest neighbor search is conducted to find - besides others - "SciFi Writer".

Topics of the last #ise2023 lecture; The Graph in #KnowledgeGraphs, Knowledge Graph Completion, A Brief History of Large Language Models, and Knowledge Graphs and Large Language Models. I will highlight some topics with the upcoming toots...
Slides: https://drive.google.com/file/d/1atNvMYNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link
#llms #languagemodels #deeplearning #linkprediction #kgc #lecture #machinelearning #transformers #gpt @fizise @enorouzi

Cover Slide of the last Information Service Engineering 2023 lecture, ISE Applications 01. Picture created by ArtBot. Prompt: "The seeds of modern Artificial Intelligence were planted by philosophers who attempted to describe the process of human thinking as the mechanical manipulation of symbols. Deep learning is a class ….”, created via ArtBot, Deliberate, 2023, [CC-BY-4.0]

Thrilled to announce our new preprint "Sem@K: Is my knowledge graph embedding model semantic-aware?" on arXiv: https://arxiv.org/pdf/2301.05601.pdf
w/ Nicolas Hubert, Armelle Brun, Davy Monticolo
#knowledgeGraph #neuroSymbolicAI #artificialIntelligence #machineLearning #linkPrediction

#linkPrediction

Client Info