"Non-convolutional Graph Neural Networks" by @YuanqingWang , and @kchonyc Paper: https://t.co/UcbhnJbTUJ #graphneuralnetworks

Following the "Tutorial on #UserProfiling with #GraphNeuralNetworks and Related Beyond-Accuracy Perspectives" at #UMAP2023 by @erasmopurif11, @ludovicoboratto and @ernestowdeluca 🚀

It has been a long time since I did an online course 👨‍🎓 . I was focused on my work this year with #GraphNeuralNetworks as my niche and never got the time or the mental fortitude to catch up to the intimidating and overwhelming amount of progress being made in the #LLM and #genai

"Homomorphism Counts as Structural Encodings for Graph Learning" by @mmbronstein, @ismaililkanc, @mat_lanzinger et al. #MachineLearning #graphneuralnetworks

"Future Directions in Foundations of Graph Machine Learning" by @HaggaiMaron ,@ismaililkanc, @ffabffrasca, @dereklim_lzh, @mmbronstein et al. Paper: https://t.co/mhgiWxGNlV #graphneuralnetworks

"GraphAny: A Foundation Model for Node Classification on Any Graph" by @AndyJiananZhao, @michael_galkin, @mmbronstein, @zhu_zhaocheng, @tangjianpku et al. Paper: https://t.co/Io0iPbjEV0 #graphneuralnetworks #foundationmodels

"Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning" by @ocariz__ ,@ottogin1 , Anastasis Kratsios, @mmbronstein,@epomqo Paper: https://t.co/bz7HTfDtvb #graphneuralnetworks

Talk 5 featured Prof. Biswarup Pathak from the Department of Chemistry, IIT Indore, presenting an insightful lecture on “Graph Neural Network for High-Throughput Screening of Nanocluster Catalysts.” 🤖🔬 #NGFM2025 #IITDharwad #IITIndore #ChemistryResearch #GraphNeuralNetworks

"Link Prediction with Relational Hypergraphs" by @hxyscott, @mmbronstein , @ismaililkanc et al. Paper: https://t.co/XloIlt6yIS #graphneuralnetworks

Banks lose $442 BILLION to fraud yearly! 🤯 Our new system uses Graph Neural Networks & Neo4j to catch what traditional ML misses. See how we built it. #ArtificialIntelligence #GraphNeuralNetworks #FraudDetection https://t.co/ZaFCt4JB99

How does over-squashing affect the power of GNNs? Di Giovanni et al.: https://t.co/7tbIYKLZQm #GraphNeuralNetworks #GNN #DeepLearning

"Graph Low-Rank Adapters of High Regularity for Graph Neural Networks and Graph Transformers" by Pantelis Papageorgiou, @ocariz__, Anastasis Kratsios, @mmbronstein Paper: https://t.co/nq5BHFZ30G Code: https://t.co/Sv4K8YwDOG #graphneuralnetworks

🚀 Advancing Pedestrian Trajectory Prediction with AI! D-STGCN: Dynamic #Pedestrian Trajectory Prediction Using Spatio-Temporal Graph Convolutional #Networks. 📖 Read more about this: https://t.co/LcbwtOyv67 #AI #MachineLearning #GraphNeuralNetworks #AutonomousSystems

How does over-squashing affect the power of GNNs? Di Giovanni et al.: https://t.co/n7ALFK75ys #GraphNeuralNetworks #GNN #DeepLearning

Using an approach that resembles dynamical mean-field theory, researchers detail how the architecture of a graph convolutional network must scale with depth to avoid oversmoothing and demonstrate how to deal with continuous #GraphNeuralNetworks. 🔗 https://t.co/las6npUQVX

Everything is Connected: Graph Neural Networks Petar Veličković : https://t.co/qFGbYcK8wl #ArtificialIntelligence #GNN #GraphNeuralNetworks

Want to try #GraphNeuralNetworks? Or expand your expertise? Join our #GNNs Masterclass to kick off 2023 with crystal-clear vision on how you can succeed with GNNs. Featuring: ✔️ GNN performance tips ✔️ OGB-winning models ✔️ Free GNN access in IPU cloud https://t.co/kk96TuFJYw

Take this self-paced Deep Learning Institute course and learn the basic concepts, implementations, and applications of #graphneuralnetworks. Be able to build and efficiently train GNN-based models. Enroll now: https://t.co/pwUwUOrqCG

Everything is Connected: Graph Neural Networks Petar Veličković : https://t.co/LaH39gWsf1 #ArtificialIntelligence #GNN #GraphNeuralNetworks