Message Passing Neural Networks Courses and Certifications

Valence Labs

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Explore subgraph GNNs, their symmetries, and expressive power. Gain insights into node-based methods, IGNs, and a novel architecture for improved graph modeling performance.

• YouTube
• 1 hour 21 minutes
• On-Demand
• Free Video

Applied Algebraic Topology Network

Yusu Wang - Graph Neural Network: Representational Power and Limitations

Explore graph neural networks' power and limitations, focusing on representation capabilities, Weisfeiler-Lehman tests, and universal approximation results for informed practical applications.

• YouTube
• 35 minutes
• On-Demand
• Free Video

Valence Labs

Ewald-Based Long-Range Message Passing for Molecular Graphs

Explore Ewald message passing for molecular graphs, enhancing long-range interactions in neural networks. Learn about its implementation, benefits, and impact on energy predictions for diverse molecular structures.

• YouTube
• 1 hour 26 minutes
• On-Demand
• Free Video

Simons Institute

Higher Order Graph Neural Networks with P-Tensors

Explore advanced graph neural networks using P-tensors to overcome message passing limitations while maintaining equivariance and improving expressiveness for complex graph structures.

• YouTube
• 1 hour 10 minutes
• On-Demand
• Free Video

Valence Labs

MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields

Explore higher-order equivariant message passing neural networks for fast, accurate force fields in computational chemistry. Learn about MACE's innovative approach using four-body messages to enhance efficiency and accuracy.

• YouTube
• 1 hour 23 minutes
• On-Demand
• Free Video

Discover AI

Topological Message Passing: From Graph Neural Networks to Simplicial Complexes on CW Networks

Delve into advanced Graph Neural Network concepts, exploring topological message passing, simplicial complexes, and high-dimensional interactions for computational graph networks and molecular design applications.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Message Passing Neural Networks for Atomistic Systems - Molecules

Explore message passing neural networks for molecular systems, focusing on their application in quantum mechanics and multiscale approaches to atomistic modeling.

• YouTube
• 24 minutes
• On-Demand
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Message Passing Neural Networks for Atomistic Systems - Materials - IPAM at UCLA

Explore message passing neural networks for atomistic systems, focusing on thermal transport simulations and diffusion in materials science, with practical examples and convergence tests.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Graph Neural Networks - Architectures and Message Passing - Lecture 5

Explore graph neural networks, their connections to MLPs and CNNs, message passing algorithms, and theoretical limitations on expressive power with practical implications.

• YouTube
• 1 hour 21 minutes
• On-Demand
• Free Video

Discover AI

The Future of Graph Neural Networks - Beyond Message Passing

Explore advanced concepts in Graph Neural Networks, focusing on topological spaces, dyadic systems, and future developments beyond traditional message passing approaches.

• YouTube
• 14 minutes
• On-Demand
• Free Video

Discover AI

AI-Driven Drug Repurposing: Multi-Agent Approach in Bioinformatics

Explore how three AI agents work together to revolutionize drug discovery through molecular binding prediction, knowledge graph analysis, and scientific literature mining for faster medical breakthroughs.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Unified Understanding of E(3)-Equivariant Interatomic Potentials - Theory and Applications

Explore E(3)-equivariant interatomic potentials, covering theory, applications, and advancements in machine learning approaches for quantum mechanics and molecular dynamics simulations.

• YouTube
• 44 minutes
• On-Demand
• Free Video

Valence Labs

Is Distance Matrix Enough for Geometric Deep Learning?

Explore geometric deep learning limitations and k-DisGNNs' potential in capturing high-order geometric information, unifying models, and achieving universal function approximation for geometric graphs.

• YouTube
• 1 hour 4 minutes
• On-Demand
• Free Video

Valence Labs

DRew: Dynamically Rewired Message Passing with Delay

Explore a novel framework for enhancing message passing neural networks, addressing over-squashing and improving long-range interactions through dynamic rewiring and delay mechanisms.

• YouTube
• 59 minutes
• On-Demand
• Free Video

Centre International de Rencontres Mathématiques

Subgraph-Based Networks for Expressive, Efficient, and Domain-Independent Graph Learning

Explore subgraph-based networks for expressive, efficient, and domain-independent graph learning. Gain insights into equivariant subgraph aggregation and symmetry principles.

• YouTube
• 50 minutes
• On-Demand
• Free Video