Stanford CS224W: ML with Graphs | 2021 | Lecture 16.1 - Limitations of Graph Neural Networks
For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/3nDnFHr
Jure Leskovec
Computer Science, PhD
In this lecture, we will talk about advanced GNN topics. We will first discuss the limitations of the Graph Neural Networks that we have introduced so far. We summarize 2 main imperfections of existing GNNs. First, existing GNNs will always fail on certain position-aware tasks, where we want to embed nodes based on their positions in the graph rather than their neighborhood structure; the solution we will introduce is Position-aware Graph Neural Networks. Second, the message passing GNNs we have introduced have expressive power upper bounded by the WL test; we will discuss how to overcome this limitation by introducing Identity-aware Graph Neural Networks.
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 16.1 - Limitations of Graph Neural Networks канала Stanford Online
Jure Leskovec
Computer Science, PhD
In this lecture, we will talk about advanced GNN topics. We will first discuss the limitations of the Graph Neural Networks that we have introduced so far. We summarize 2 main imperfections of existing GNNs. First, existing GNNs will always fail on certain position-aware tasks, where we want to embed nodes based on their positions in the graph rather than their neighborhood structure; the solution we will introduce is Position-aware Graph Neural Networks. Second, the message passing GNNs we have introduced have expressive power upper bounded by the WL test; we will discuss how to overcome this limitation by introducing Identity-aware Graph Neural Networks.
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 16.1 - Limitations of Graph Neural Networks канала Stanford Online
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![The Role of Water and #Energy for Circular Economies with Will Tarpeh](https://i.ytimg.com/vi/NrYOMNCY0nk/default.jpg)
![Antonio Del Santo talks about his experience in Stanford's Digital Health Product Development Course](https://i.ytimg.com/vi/KTuhZAMKCWY/default.jpg)
![Stanford Seminar - Human-AI Interaction Under Societal Disagreement](https://i.ytimg.com/vi/Y3Kj_2ZNRfw/default.jpg)
![What does the future hold for Natural Language Processing? - Andrew Ng & Chris Manning](https://i.ytimg.com/vi/yHPbFXCDr3k/default.jpg)
![Stanford Webinar - Building Safe and Reliable Autonomous Systems](https://i.ytimg.com/vi/IDvdyv_49-M/default.jpg)
![Stanford Seminar - Applications of Generative Design for Fabrication in Healthcare Settings](https://i.ytimg.com/vi/-oSkiUHlgo0/default.jpg)
![Stanford Webinar - How [You] Can Use ChatGPT to Increase Your Creative Output](https://i.ytimg.com/vi/OXHyVNTcY2k/default.jpg)
![What does the future hold for AI and Robotics? - Chelsea Finn & Andrew Ng](https://i.ytimg.com/vi/yCn8VCx49jA/default.jpg)
![What inspired you to choose AI and Robotics as a profession? - Chelsea Finn & Andrew Ng](https://i.ytimg.com/vi/CggrzkwKM9k/default.jpg)
![Andrew Ng and Fei-Fei Li Discuss Human-Centered Artificial Intelligence - Stanford Online](https://i.ytimg.com/vi/UNhC6Ox0T0o/default.jpg)
![What advice do you have for getting started in AI & Machine Learning? - Fei-Fei Li & Andrew Ng](https://i.ytimg.com/vi/cxJi15eXWJU/default.jpg)
![Stanford Seminar - Intelligence Augmentation through the Lens of Interactive Data Visualization](https://i.ytimg.com/vi/wZc1Rq5FtXc/default.jpg)
![Is a Career in AI and Machine Learning Right for Me? - Fei-Fei Li & Andrew Ng](https://i.ytimg.com/vi/ltTVcdItq1U/default.jpg)
![Stanford Seminar - Going beyond the here and now: Counterfactual simulation in human cognition](https://i.ytimg.com/vi/eXC8BMMr-DA/default.jpg)
![Stanford Seminar - #TechFail: From Intersectional (In)Accessibility to Inclusive Design](https://i.ytimg.com/vi/nqTvNcFz0so/default.jpg)
![Building Business Models - Online Course Overview](https://i.ytimg.com/vi/Y9uHmN-E-Yw/default.jpg)
![Stanford Seminar - Robots in Dynamic Tasks: Learning, Risk, and Safety](https://i.ytimg.com/vi/e5msdWlhoa4/default.jpg)
![Stanford Seminar - Designing the Interactive Paper](https://i.ytimg.com/vi/Z-2ka33IPRk/default.jpg)
![Digital Health Product Development: Course Overview](https://i.ytimg.com/vi/ViUfzX-zZV0/default.jpg)
![Stanford Seminar - Towards Shape Changing Displays and Shape Changing Robots](https://i.ytimg.com/vi/3eCkGvvMGA4/default.jpg)
![Stanford Seminar - From open-source to safety-certified robotic software](https://i.ytimg.com/vi/tuoHL-CWhfY/default.jpg)