Lmst

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

http://jmlr.org/papers/v26/24-2130.html

#graphneuralnetworks #graphs #graph

Interpretable Physics-Informed Graph Neural Networks For Flood Forecasting
--
https://doi.org/10.1111/mice.13484 <-- shared paper
--
https://github.com/MehdiTaghizadehUVa/modulus/tree/main/examples/weather/flood_modeling/hydrographnet <-- shared GitHub repository
--
#GIS #spatial #mapping #FloodForecasting #GraphNeuralNetworks #PhysicsInformedAI #Hydrology #ClimateResilience #ScientificMachineLearning #CivilEngineering #HydroGraphNet #PhyiscsNeMo #hydrology #water #flood #flooding #spatialanalysis #spatiotemporal #climatechange #model #modeling #machinelearning #AI #extremeweather #prediction #forecasting #planning #humanimpacts #loss #lossoflife #publicsafety #cost #economics #infrastructure #risk #hazard #disaster #mitigation #preparedness #naturaldisaster #HydroGraphNet #floodforecasting #dynamics #remotesensing #earthobservation

🧬 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: https://doi.org/10.1016/j.csbj.2025.03.014

📚 CSBJ: https://www.csbj.org/

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

GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings. Computational and Structural Biotechnology Journal, DOI: https://doi.org/10.1016/j.csbj.2025.03.014

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...

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.

https://distill.pub/2021/gnn-intro/

#GraphNeuralNetworks #GNN #ComputerScience #neuroscience

Gentle Introduction to Graph Neural Networks
https://distill.pub/2021/gnn-intro/
https://news.ycombinator.com/item?id=42468214
https://en.wikipedia.org/wiki/Graph_neural_network

* specialized artificial neural networks designed for tasks whose inputs are graphs
* GNN use pairwise message passing
* graph nodes iteratively update their representations by exchanging information w. their neighbors

#ML #ANN #NeuralNetworks #graphs #GraphNeuralNetworks #GNN #RepresentationLearning

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

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: https://bit.ly/3UXutls

#transcript included

#PyG #GNNs #opensource #ML #DataWarehouse

🆕 Newsletter 🚀 Dive into the world of AI security! Discover essential strategies to shield your generative AI apps from prompt injection risks. Stay ahead in the AI safety game!
#GenerativeAI #LLMs #PromptInjection #Cybersecurity #EthicalAI #ResponsibleAI #AISafety #AnomalyDetection #WeatherForecasting #GraphNeuralNetworks #DeepLearning #ClimateChange
https://gradientflow.substack.com/p/securing-ai-addressing-the-emerging

Interpretable Graph Neural Networks for Tabular Data
https://arxiv.org/abs/2308.08945
Discussion: https://news.ycombinator.com/item?id=37269376

* GNN essentially deep NN black-box models
* IGNNet: Interpretable Graph Neural Network for tab data
* notable HN comment, resp. to critique: " Right, the significance of orig. article & related research is ChatGPT-like models don't handle tabular data well & there's need for things that do"

#DataProcessing #GraphNeuralNetworks #GNN #TabularData #GPT #LLM #IGNNet

Interpretable Graph Neural Networks for Tabular Data

Figure 1: An overview of our proposed approach. Each data instance is represented as a graph by embedding the feature values into a higher dimensionality, and the edge between two features (nodes) is the correlation value. Multiple iterations of message passing are then applied. Finally, the learned node representation is projected into a single value, and a whole graph representation is obtained by concatenating the projected values.

Figure 2: IGNNet default architecture. It starts with the embedding layer, a linear transformation from one dimension to 64 dimensions. A Relu activation function follows each message-passing layer and each green block as well. The feedforward network at the end has no activation functions between layers to ensure a linear transformation into a single value. A sigmoid activation function follows the feedforward network to obtain the final value for each feature between 0 and 1.

Article: https://arxiv.org/pdf/2308.08945.pdf

Discussion (Hacker News): https://news.ycombinator.com/item?id=37269376

Addendae 4

Graph Structure f. Point Clouds: Geometric Attention All You Need
https://arxiv.org/abs/2307.16662

* partly intersect my interest in knowledge graphs, fully-connected networks, and transformers in NLP and ML
* length of that discussion - though brief - exceeds the Mastodon 500-char limit, so I moved that discussion here:

Fully-connected graphs: Graph neural networks, transformers
https://persagen.com/docs/gnn-transformers.html

#GNN #attention #transformers #GraphTheory #NeuralNetworks #GraphNeuralNetworks

Hierarchical GNNs for Large Graph Generation
https://arxiv.org/abs/2306.11412

Large graphs are present in a variety of domains, including social networks, civil infrastructure, & the physical sciences. ... Graph generation is similarly widespread, with applications in drug discovery, network analysis & synthetic datasets among others. While GNN (Graph Neural Network) models have been applied in these domains their high in-memory costs restrict them to small graphs. ...

#GNN #graphs #GraphNeuralNetworks

#arxivfeed :

"CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis"
https://arxiv.org/abs/2301.01642

#Neuroscience #Neuro #ComputationalNeuroscience #MachineLearning #GraphNeuralNetworks #Psychiatry #FunctionalConnectivity #CausalInference

Presenting a hybrid algorithm able to find influential groups of users in: “Boosting a Genetic Algorithm with #GraphNeuralNetworks for Multi-Hop #InfluenceMaximization in Social Networks” by CC Sartori, C. Blum. @FedCSIS
2022, ACSIS Vol. 30 p. 363–371; http://tinyurl.com/bdhr4y6s