home.social

#graphneuralnetworks — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #graphneuralnetworks, aggregated by home.social.

  1. 🚀 Excited to share that a survey paper from our RCLN team has been accepted at IJCAI 2026! This work has been done in collaboration with CentraleSupélec.
    "Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey" By Hugo Attali, Nathalie Pernelle, Davide Buscaldi, and Fragkiskos D. Malliaros.

    📎 arxiv.org/abs/2411.17429

    Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where information from distant nodes is excessively compressed, and over-smoothing, where repeated propagation makes node representations indistinguishable. Both phenomena stem from the interaction between message passing and the input topology, ultimately degrading information flow and limiting the performance of GNNs.Our survey also opens a broader discussion on the limits and open questions of graph rewiring: when is modifying the topology truly necessary? How can observed improvements be properly attributed to connectivity changes rather than feature-driven effects? We argue that progress in this area will require clearer problem formulations, more explicit assumptions, and evaluation protocols that make results robust and comparable across settings positioning graph rewiring as a principled structural intervention to better understand how topology shapes learning in GNNs.

    Looking forward to presenting our work at IJCAI 2026 at Bremen!

    #GNN #MachineLearning #IJCAI2026 #GraphNeuralNetworks #AI #DeepLearning #Research #LIPN

  2. A new AI method uses Graphical Mutual Information to learn powerful graph embeddings without labels, outperforming top unsupervised models. hackernoon.com/a-new-way-to-tr #graphneuralnetworks

  3. A new AI method uses Graphical Mutual Information to learn powerful graph embeddings without labels, outperforming top unsupervised models. hackernoon.com/a-new-way-to-tr #graphneuralnetworks

  4. 2026 marks the turning point: adaptive Graph Neural Networks are finally joining forces with Large Language Models beyond the lab, powering context‑aware AI in real‑world enterprises. Discover how GNN‑LLM integration reshapes AI pipelines, boosts adaptability, and delivers open‑source‑friendly solutions for businesses. #GraphNeuralNetworks #LargeLanguageModels #AdaptiveAI #EnterpriseAI

    🔗 aidailypost.com/news/2026-mark

  5. Neo4j’s new graph‑neural fraud detector hits a solid ROC AUC, but its default threshold flags every transaction as suspicious. The paper walks through the confusion matrix, real‑time constraints, and how tweaking thresholds can restore balance. Open‑source fans will love the dive into practical GNN tuning. Curious? Read on for the full breakdown. #Neo4j #GraphNeuralNetworks #FraudDetection #ROCcurve

    🔗 aidailypost.com/news/neo4j-gra

  6. 🌿 Can graph neural networks be taught to think in the language of chemistry?

    🔗 Leveraging molecular graphs for natural product classification. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.08

    📚 CSBJ: csbj.org/

    #AI #DrugDiscovery #GraphNeuralNetworks #NaturalProducts #DeepLearning #Cheminformatics

  7. 'GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia', by Carlo Lucibello, Aurora Rossi.

    jmlr.org/papers/v26/24-2130.ht

    #graphneuralnetworks #graphs #graph

  8. 'GraphNeuralNetworks.jl: Deep Learning on Graphs with Julia', by Carlo Lucibello, Aurora Rossi.

    jmlr.org/papers/v26/24-2130.ht

    #graphneuralnetworks #graphs #graph

  9. 🧬 Ready for AI to crack the RNA-disease code?

    🔗 GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.03

    📚 CSBJ: csbj.org/

    #AIinBiomedicine #GraphNeuralNetworks #LLM #ncRNA #snoRNA #CancerResearch #Bioinformatics #PrecisionMedicine #XAI #Genomics

  10. 🧬 Ready for AI to crack the RNA-disease code?

    🔗 GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.03

    📚 CSBJ: csbj.org/

    #AIinBiomedicine #GraphNeuralNetworks #LLM #ncRNA #snoRNA #CancerResearch #Bioinformatics #PrecisionMedicine #XAI #Genomics

  11. 🧬 Ready for AI to crack the RNA-disease code?

    🔗 GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.03

    📚 CSBJ: csbj.org/

    #AIinBiomedicine #GraphNeuralNetworks #LLM #ncRNA #snoRNA #CancerResearch #Bioinformatics #PrecisionMedicine #XAI #Genomics

  12. 🧬 Ready for AI to crack the RNA-disease code?

    🔗 GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.03

    📚 CSBJ: csbj.org/

    #AIinBiomedicine #GraphNeuralNetworks #LLM #ncRNA #snoRNA #CancerResearch #Bioinformatics #PrecisionMedicine #XAI #Genomics

  13. 🧬 Ready for AI to crack the RNA-disease code?

    🔗 GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: doi.org/10.1016/j.csbj.2025.03

    📚 CSBJ: csbj.org/

    #AIinBiomedicine #GraphNeuralNetworks #LLM #ncRNA #snoRNA #CancerResearch #Bioinformatics #PrecisionMedicine #XAI #Genomics

  14. Tenemos cita el 20 de febrero 🔥 Nos vemos en BBVA AI Factory para hablar embeddings para contratación financiera y de redes neuronales de grafos. Estamos probando @guild.host, ¡reserva tu plaza aquí! 👇 guild.host/events/embed... #PyData #PyDataMadrid #python #embeddings #GraphNeuralNetworks

    📄 Embeddings para contratación...

  15. An introduction to graph neural networks, with a section on "where to find them", that does not mention at all neural circuits or connectomes. WTF.

    distill.pub/2021/gnn-intro/

    #GraphNeuralNetworks #GNN #ComputerScience #neuroscience

  16. An introduction to graph neural networks, with a section on "where to find them", that does not mention at all neural circuits or connectomes. WTF.

    distill.pub/2021/gnn-intro/

    #GraphNeuralNetworks #GNN #ComputerScience #neuroscience

  17. 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"!

    📎 arxiv.org/pdf/2303.00286.pdf

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

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

  18. 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"!

    📎 arxiv.org/pdf/2303.00286.pdf

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

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

  19. Dive into the world of #GraphNeuralNetworks (GNNs)!

    Discover their advantages over traditional machine learning and have a quick primer on graph representation learning using PyG, a popular open-source GNN library.

    🎥 Watch now on #InfoQ: bit.ly/3UXutls

    #transcript included

    #PyG #GNNs #opensource #ML #DataWarehouse

  20. Dive into the world of (GNNs)!

    Discover their advantages over traditional machine learning and have a quick primer on graph representation learning using PyG, a popular open-source GNN library.

    🎥 Watch now on : bit.ly/3UXutls

    included

  21. ROLAND: A new framework to repurpose static GNNs to dynamic GNNs.

    In real life, interaction graphs are often dynamic: edges and nodes change with time 🕸️

    ROLAND ia built with PyG @PyTorch GraphGym to efficiently explore the GNN design space.

    arxiv.org/abs/2208.07239

    github.com/snap-stanford/rolan

    #graph #graphneuralnetworks #gnn #neuralnetwork #ann #nn #machinelearning #datascience

  22. ROLAND: A new framework to repurpose static GNNs to dynamic GNNs.

    In real life, interaction graphs are often dynamic: edges and nodes change with time 🕸️

    ROLAND ia built with PyG @PyTorch GraphGym to efficiently explore the GNN design space.

    arxiv.org/abs/2208.07239

    github.com/snap-stanford/rolan

    #graph #graphneuralnetworks #gnn #neuralnetwork #ann #nn #machinelearning #datascience