Stanford CS224W: ML with Graphs | 2021 | Lecture 16.2 - Position-Aware Graph Neural Networks
For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3EpTPwM
Jure Leskovec
Computer Science, PhD
We introduce the idea of Position-aware for graphs. To start, we define position-aware tasks, where we would like to classify nodes based on their positions in the graph. We demonstrate that certain position-aware tasks will always cause GNNs to fail. Our solution is the Position-aware Graph Neural Networks (P-GNN). The key idea of P-GNN is to introduce randomly selected anchors node, where we will embed all the nodes by computing their shortest path distances to these anchor nodes. To save the number of anchors needed, we further generalize the notion of anchor to anchor-sets, where each anchor-set contains a varied number of nodes.
You can find more details on the P-GNN paper. https://arxiv.org/abs/1906.04817
To follow along with the course schedule and syllabus, visit:
http://web.stanford.edu/class/cs224w/
#machinelearning #machinelearningcourse
Видео Stanford CS224W: ML with Graphs | 2021 | Lecture 16.2 - Position-Aware Graph Neural Networks канала Stanford Online
Jure Leskovec
Computer Science, PhD
We introduce the idea of Position-aware for graphs. To start, we define position-aware tasks, where we would like to classify nodes based on their positions in the graph. We demonstrate that certain position-aware tasks will always cause GNNs to fail. Our solution is the Position-aware Graph Neural Networks (P-GNN). The key idea of P-GNN is to introduce randomly selected anchors node, where we will embed all the nodes by computing their shortest path distances to these anchor nodes. To save the number of anchors needed, we further generalize the notion of anchor to anchor-sets, where each anchor-set contains a varied number of nodes.
You can find more details on the P-GNN paper. https://arxiv.org/abs/1906.04817
To follow along with the course schedule and syllabus, visit:
http://web.stanford.edu/class/cs224w/
#machinelearning #machinelearningcourse
Видео Stanford CS224W: ML with Graphs | 2021 | Lecture 16.2 - Position-Aware Graph Neural Networks канала Stanford Online
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Stanford Seminar - Fight over the Law of Software APIs & stories from Electronic Frontier FoundationStanford CS224W: Machine Learning with Graphs | 2021 | Lecture 17.3 - Cluster GCN: Scaling up GNNsStanford Seminar - Intelligence Augmentation through the Lens of Interactive Data VisualizationStanford Seminar - Get in touch: Tactile perception for human-robot systemsLearner Spotlight: Andrew PelosiAntonio Del Santo talks about his experience in Stanford's Digital Health Product Development CourseStanford Seminar - Human-AI Interaction Under Societal DisagreementStudent Spotlight: Daphne Wallbridge talks about the Creativity and Design Thinking ProgramWebinar - Big Breaches: What We Learned From the World’s Most Disruptive Cybersecurity AttacksStanford Seminar - Interview with Amy Chang of AccompanyStanford Webinar - Natural Language Understanding Student Project Showcase - Plus AI Program Q&ABuilding Energy Efficiency: Technology, Policy & Policy (bee.stanford.edu)Stanford CS224W: Machine Learning with Graphs | 2021 | Lecture 10.2 - Knowledge Graph CompletionStanford Seminar - Towards Shape Changing Displays and Shape Changing RobotsStanford Workshop - Innovation at Work Prototyping PreviewStanford Seminar - Improving Computational Efficiency for Powered Descent GuidanceStanford Seminar - Incorporating Sample Efficient Monitoring into Learned AutonomyStanford CS224W: ML with Graphs | 2021 | Lecture 16.4 - Robustness of Graph Neural NetworksNetwork and Information Security: Reflections on the Past and the Look AheadDecarbonizing the Grid: Technology and Policy (webcast)Stanford Seminar - ML Explainability Part 3 I Post hoc Explanation Methods