Pierre Monnin<p>Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction<br /><a href="https://2024.eswc-conferences.org/wp-content/uploads/2024/04/146640020.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">2024.eswc-conferences.org/wp-c</span><span class="invisible">ontent/uploads/2024/04/146640020.pdf</span></a></p><p><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="tag">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/syntheticData" class="mention hashtag" rel="tag">#<span>syntheticData</span></a> <a href="https://sigmoid.social/tags/neuroSymbolicAI" class="mention hashtag" rel="tag">#<span>neuroSymbolicAI</span></a> <a href="https://sigmoid.social/tags/ArtificialIntelligence" class="mention hashtag" rel="tag">#<span>ArtificialIntelligence</span></a> <a href="https://sigmoid.social/tags/semanticWeb" class="mention hashtag" rel="tag">#<span>semanticWeb</span></a> <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a> <a href="https://sigmoid.social/tags/graphEmbedding" class="mention hashtag" rel="tag">#<span>graphEmbedding</span></a></p>
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!
Administered by:
Server stats:
588active users
sigmoid.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.4
#linkprediction
0 posts · 0 participants · 0 posts today
Pierre Monnin<p>PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips <a href="https://2024.eswc-conferences.org/wp-content/uploads/2024/04/146640336-1.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">2024.eswc-conferences.org/wp-c</span><span class="invisible">ontent/uploads/2024/04/146640336-1.pdf</span></a></p><p><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="tag">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/syntheticData" class="mention hashtag" rel="tag">#<span>syntheticData</span></a> <a href="https://sigmoid.social/tags/neuroSymbolicAI" class="mention hashtag" rel="tag">#<span>neuroSymbolicAI</span></a> <a href="https://sigmoid.social/tags/ArtificialIntelligence" class="mention hashtag" rel="tag">#<span>ArtificialIntelligence</span></a> <a href="https://sigmoid.social/tags/semanticWeb" class="mention hashtag" rel="tag">#<span>semanticWeb</span></a> <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a> <a href="https://sigmoid.social/tags/graphEmbedding" class="mention hashtag" rel="tag">#<span>graphEmbedding</span></a></p>
Pierre Monnin<p>Very glad to announce that we got 2 best paper awards at <a href="https://sigmoid.social/tags/ESWC2024" class="mention hashtag" rel="tag">#<span>ESWC2024</span></a> for our works about PyGraft (resource track) and semantically enhanced loss functions to learn graph <a href="https://sigmoid.social/tags/embedding" class="mention hashtag" rel="tag">#<span>embedding</span></a> (research track)! Congratulations Nicolas Hubert!</p><p><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="tag">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/syntheticData" class="mention hashtag" rel="tag">#<span>syntheticData</span></a> <a href="https://sigmoid.social/tags/neuroSymbolicAI" class="mention hashtag" rel="tag">#<span>neuroSymbolicAI</span></a> <a href="https://sigmoid.social/tags/ArtificialIntelligence" class="mention hashtag" rel="tag">#<span>ArtificialIntelligence</span></a> <a href="https://sigmoid.social/tags/semanticWeb" class="mention hashtag" rel="tag">#<span>semanticWeb</span></a> <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a> <a href="https://sigmoid.social/tags/graphEmbedding" class="mention hashtag" rel="tag">#<span>graphEmbedding</span></a></p>
Pierre Monnin<p>Very happy to announce our new paper accepted in <span class="h-card" translate="no"><a href="https://sigmoid.social/@eswc_conf" class="u-url mention">@<span>eswc_conf</span></a></span><br /> <a href="https://sigmoid.social/tags/ESWC2024" class="mention hashtag" rel="tag">#<span>ESWC2024</span></a>: "Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction"!</p><p>📎 <a href="https://arxiv.org/pdf/2303.00286.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2303.00286.pdf</span><span class="invisible"></span></a></p><p>w/ N. Hubert, A. Brun, and D. Monticolo</p><p><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="tag">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/semanticWeb" class="mention hashtag" rel="tag">#<span>semanticWeb</span></a> <a href="https://sigmoid.social/tags/machineLearning" class="mention hashtag" rel="tag">#<span>machineLearning</span></a> <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a> <a href="https://sigmoid.social/tags/neurosymbolicAI" class="mention hashtag" rel="tag">#<span>neurosymbolicAI</span></a> <a href="https://sigmoid.social/tags/artificialIntelligence" class="mention hashtag" rel="tag">#<span>artificialIntelligence</span></a> <a href="https://sigmoid.social/tags/linkedOpenData" class="mention hashtag" rel="tag">#<span>linkedOpenData</span></a> <a href="https://sigmoid.social/tags/graphEmbeddings" class="mention hashtag" rel="tag">#<span>graphEmbeddings</span></a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="tag">#<span>embeddings</span></a> <a href="https://sigmoid.social/tags/graphNeuralNetworks" class="mention hashtag" rel="tag">#<span>graphNeuralNetworks</span></a></p>
Pierre Monnin<p>Our paper "PyGraft: Configurable Generation of Synthetic <a href="https://sigmoid.social/tags/Schemas" class="mention hashtag" rel="tag">#<span>Schemas</span></a> and <a href="https://sigmoid.social/tags/KnowledgeGraphs" class="mention hashtag" rel="tag">#<span>KnowledgeGraphs</span></a> at Your Fingertips" has been accepted in <span class="h-card" translate="no"><a href="https://sigmoid.social/@eswc_conf" class="u-url mention">@<span>eswc_conf</span></a></span> <a href="https://sigmoid.social/tags/ESWC2024" class="mention hashtag" rel="tag">#<span>ESWC2024</span></a>!</p><p>Paper: <a href="https://arxiv.org/pdf/2309.03685.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2309.03685.pdf</span><span class="invisible"></span></a><br />Code: <a href="https://github.com/nicolas-hbt/pygraft" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">github.com/nicolas-hbt/pygraft</span><span class="invisible"></span></a></p><p>PyGraft is a configurable <a href="https://sigmoid.social/tags/Python" class="mention hashtag" rel="tag">#<span>Python</span></a> tool to generate both synthetic <a href="https://sigmoid.social/tags/schemas" class="mention hashtag" rel="tag">#<span>schemas</span></a> and <a href="https://sigmoid.social/tags/knowledgeGraphs" class="mention hashtag" rel="tag">#<span>knowledgeGraphs</span></a> easily, supporting several RDFS and OWL constructs. These <a href="https://sigmoid.social/tags/datasets" class="mention hashtag" rel="tag">#<span>datasets</span></a> are useful for, e.g., <a href="https://sigmoid.social/tags/neurosymbolicAI" class="mention hashtag" rel="tag">#<span>neurosymbolicAI</span></a>, <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a>, <a href="https://sigmoid.social/tags/nodeClassification" class="mention hashtag" rel="tag">#<span>nodeClassification</span></a>, <a href="https://sigmoid.social/tags/nodeClustering" class="mention hashtag" rel="tag">#<span>nodeClustering</span></a>, <a href="https://sigmoid.social/tags/ontology" class="mention hashtag" rel="tag">#<span>ontology</span></a> repairing</p>
Harald Sack<p>2nd add on to our free MOOC lecture series on <a href="https://sigmoid.social/tags/KnowledgeGraphs" class="mention hashtag" rel="tag">#<span>KnowledgeGraphs</span></a> is a colab notebook on knowledge graph completion with TransE through which my colleagues Ann Tan and <span class="h-card" translate="no"><a href="https://sigmoid.social/@MahsaVafaie" class="u-url mention">@<span>MahsaVafaie</span></a></span> will guide you in the video.<br /><a href="https://sigmoid.social/tags/OpenHPI" class="mention hashtag" rel="tag">#<span>OpenHPI</span></a> video: <a href="https://open.hpi.de/courses/knowledgegraphs2023/items/48Sn5Tr9RKo24RXu7OwgOz" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">open.hpi.de/courses/knowledgeg</span><span class="invisible">raphs2023/items/48Sn5Tr9RKo24RXu7OwgOz</span></a><br />youtube video: <a href="https://www.youtube.com/watch?v=IVTVzgCbHOw&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=67" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=IVTVzgCbHO</span><span class="invisible">w&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=67</span></a><br />colab notebook: <a href="https://colab.research.google.com/drive/104ad-kusmzfYgkK_L8ETWUAjfdreE9e2#scrollTo=fQ08XPbaZgQ4" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">colab.research.google.com/driv</span><span class="invisible">e/104ad-kusmzfYgkK_L8ETWUAjfdreE9e2#scrollTo=fQ08XPbaZgQ4</span></a></p><p><span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention">@<span>fizise</span></a></span> <span class="h-card" translate="no"><a href="https://wisskomm.social/@fiz_karlsruhe" class="u-url mention">@<span>fiz_karlsruhe</span></a></span> <a href="https://sigmoid.social/tags/semanticweb" class="mention hashtag" rel="tag">#<span>semanticweb</span></a> <a href="https://sigmoid.social/tags/kge" class="mention hashtag" rel="tag">#<span>kge</span></a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="tag">#<span>embeddings</span></a> <a href="https://sigmoid.social/tags/linkprediction" class="mention hashtag" rel="tag">#<span>linkprediction</span></a> <a href="https://sigmoid.social/tags/videolecture" class="mention hashtag" rel="tag">#<span>videolecture</span></a> <a href="https://sigmoid.social/tags/video" class="mention hashtag" rel="tag">#<span>video</span></a></p>
Harald Sack<p>Knowledge Graph Embeddings (KGEs) are a very useful tool for few- and zero-shot learning. Of course Link Prediction and <a href="https://sigmoid.social/tags/KnowledgeGraph" class="mention hashtag" rel="tag">#<span>KnowledgeGraph</span></a> 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 <a href="https://sigmoid.social/tags/kg2023" class="mention hashtag" rel="tag">#<span>kg2023</span></a> lecture.<br />OpenHPI video: <a href="https://open.hpi.de/courses/knowledgegraphs2023/items/3xfeKrryLMeY45OXSwBd86" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">open.hpi.de/courses/knowledgeg</span><span class="invisible">raphs2023/items/3xfeKrryLMeY45OXSwBd86</span></a><br />youtube video: <a href="https://www.youtube.com/watch?v=UGmtYSCXsQk&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=62" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=UGmtYSCXsQ</span><span class="invisible">k&list=PLNXdQl4kBgzubTOfY5cbtxZCgg9UTe-uF&index=62</span></a><br />slides: <a href="https://zenodo.org/records/10185280" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">zenodo.org/records/10185280</span><span class="invisible"></span></a><br /><span class="h-card" translate="no"><a href="https://fedihum.org/@tabea" class="u-url mention">@<span>tabea</span></a></span> <span class="h-card" translate="no"><a href="https://fedihum.org/@sashabruns" class="u-url mention">@<span>sashabruns</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@MahsaVafaie" class="u-url mention">@<span>MahsaVafaie</span></a></span> <span class="h-card" translate="no"><a href="https://wisskomm.social/@fiz_karlsruhe" class="u-url mention">@<span>fiz_karlsruhe</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention">@<span>fizise</span></a></span> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="tag">#<span>embeddings</span></a> <a href="https://sigmoid.social/tags/linkprediction" class="mention hashtag" rel="tag">#<span>linkprediction</span></a></p>
Pierre Monnin<p>PyGraft will help you generate new and tailored benchmark KG <a href="https://sigmoid.social/tags/datasets" class="mention hashtag" rel="tag">#<span>datasets</span></a> useful in various fields including but not limited to <a href="https://sigmoid.social/tags/neurosymbolicAI" class="mention hashtag" rel="tag">#<span>neurosymbolicAI</span></a>, <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a>, <a href="https://sigmoid.social/tags/nodeClassification" class="mention hashtag" rel="tag">#<span>nodeClassification</span></a>, <a href="https://sigmoid.social/tags/nodeClustering" class="mention hashtag" rel="tag">#<span>nodeClustering</span></a>, <a href="https://sigmoid.social/tags/ontology" class="mention hashtag" rel="tag">#<span>ontology</span></a> repairing, pattern mining, reasoning, scalability studies, etc.</p><p>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 <a href="https://sigmoid.social/tags/semanticWeb" class="mention hashtag" rel="tag">#<span>semanticWeb</span></a> <a href="https://sigmoid.social/tags/machineLearning" class="mention hashtag" rel="tag">#<span>machineLearning</span></a> and other communities!</p>
Harald Sack<p>As a 2nd topic of this last <a href="https://sigmoid.social/tags/ise2023" class="mention hashtag" rel="tag">#<span>ise2023</span></a> lecture, we were discussing <a href="https://sigmoid.social/tags/KnowledgeGraph" class="mention hashtag" rel="tag">#<span>KnowledgeGraph</span></a> Completion. Most simple approach for unsupervised <a href="https://sigmoid.social/tags/linkprediction" class="mention hashtag" rel="tag">#<span>linkprediction</span></a> based on (here translation-based) knowledge graph embeddings was explained on the example of Isaac Asimov. <br />Slides: <a href="https://drive.google.com/file/d/1atNvMYNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">drive.google.com/file/d/1atNvM</span><span class="invisible">YNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link</span></a><br /><span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention">@<span>fizise</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@enorouzi" class="u-url mention">@<span>enorouzi</span></a></span> <a href="https://sigmoid.social/tags/scifi" class="mention hashtag" rel="tag">#<span>scifi</span></a> <a href="https://sigmoid.social/tags/knowledgegraphs" class="mention hashtag" rel="tag">#<span>knowledgegraphs</span></a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="tag">#<span>ai</span></a> <a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://sigmoid.social/tags/embeddings" class="mention hashtag" rel="tag">#<span>embeddings</span></a></p>
Harald Sack<p>Topics of the last <a href="https://sigmoid.social/tags/ise2023" class="mention hashtag" rel="tag">#<span>ise2023</span></a> lecture; The Graph in <a href="https://sigmoid.social/tags/KnowledgeGraphs" class="mention hashtag" rel="tag">#<span>KnowledgeGraphs</span></a>, 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...<br />Slides: <a href="https://drive.google.com/file/d/1atNvMYNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">drive.google.com/file/d/1atNvM</span><span class="invisible">YNkeKDwXP3olHXzloa09S5pzjXb/view?usp=drive_link</span></a><br /><a href="https://sigmoid.social/tags/llms" class="mention hashtag" rel="tag">#<span>llms</span></a> <a href="https://sigmoid.social/tags/languagemodels" class="mention hashtag" rel="tag">#<span>languagemodels</span></a> <a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://sigmoid.social/tags/linkprediction" class="mention hashtag" rel="tag">#<span>linkprediction</span></a> <a href="https://sigmoid.social/tags/kgc" class="mention hashtag" rel="tag">#<span>kgc</span></a> <a href="https://sigmoid.social/tags/lecture" class="mention hashtag" rel="tag">#<span>lecture</span></a> <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="tag">#<span>machinelearning</span></a> <a href="https://sigmoid.social/tags/transformers" class="mention hashtag" rel="tag">#<span>transformers</span></a> <a href="https://sigmoid.social/tags/gpt" class="mention hashtag" rel="tag">#<span>gpt</span></a> <span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention">@<span>fizise</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@enorouzi" class="u-url mention">@<span>enorouzi</span></a></span></p>
Pierre Monnin<p>Thrilled to announce our new preprint "Sem@K: Is my knowledge graph embedding model semantic-aware?" on arXiv: <a href="https://arxiv.org/pdf/2301.05601.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">arxiv.org/pdf/2301.05601.pdf</span><span class="invisible"></span></a><br />w/ Nicolas Hubert, Armelle Brun, Davy Monticolo<br /><a href="https://sigmoid.social/tags/knowledgeGraph" class="mention hashtag" rel="tag">#<span>knowledgeGraph</span></a> <a href="https://sigmoid.social/tags/neuroSymbolicAI" class="mention hashtag" rel="tag">#<span>neuroSymbolicAI</span></a> <a href="https://sigmoid.social/tags/artificialIntelligence" class="mention hashtag" rel="tag">#<span>artificialIntelligence</span></a> <a href="https://sigmoid.social/tags/machineLearning" class="mention hashtag" rel="tag">#<span>machineLearning</span></a> <a href="https://sigmoid.social/tags/linkPrediction" class="mention hashtag" rel="tag">#<span>linkPrediction</span></a></p>
TrendingLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload