How to get started with Graph ML? (Blog walkthrough)
ฝัง
- เผยแพร่เมื่อ 31 ก.ค. 2024
- ❤️ Become The AI Epiphany Patreon ❤️ ► / theaiepiphany
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
In this video, I walk you through my blog on getting started with Graph ML.
I talk about research, learning, cool Graph ML apps, resources to get you started, my GAT project, and beyond! (till infinity)
You'll learn about:
✔️ Various research tips
✔️ How to get started with Graph ML
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Medium blog: / how-to-get-started-wit...
✅ GAT project: github.com/gordicaleksa/pytor...
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Research/learning challenges
03:05 What is Graph ML? We're all graphs
05:05 Cool Graph ML applications
09:35 Fake news and fundamental science
13:20 Halicin a potent antibiotic discovered by a GNN
15:45 Contrasting Graph ML with CV and NLP
19:15 Resources - graph embedding methods
21:10 Graph Neural Networks
23:20 Top to bottom approach - high level resources
26:35 Spatial methods
30:40 Simple baselines sometimes work great!
32:25 Parallel with CNNs
33:40 GNN expressivity
36:35 Dynamic graphs
39:15 Unsupervised graph learning and geometric DL
40:55 Datasets/benchmarks and newsletter
44:15 GAT project
44:50 Related research subfields
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 BECOME A PATREON OF THE AI EPIPHANY ❤️
If these videos, GitHub projects, and blogs help you,
consider helping me out by supporting me on Patreon!
The AI Epiphany ► / theaiepiphany
One-time donation:
www.paypal.com/paypalme/theai...
Much love! ❤️
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💡 The AI Epiphany is a channel dedicated to simplifying the field of AI using creative visualizations and in general, a stronger focus on geometrical and visual intuition, rather than the algebraic and numerical "intuition".
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
👋 CONNECT WITH ME ON SOCIAL
LinkedIn ► / aleksagordic
Twitter ► / gordic_aleksa
Instagram ► / aiepiphany
Facebook ► / aiepiphany
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► / discord
📢 SUBSCRIBE TO MY MONTHLY AI NEWSLETTER:
Substack ► aiepiphany.substack.com/
💻 FOLLOW ME ON GITHUB FOR COOL PROJECTS:
GitHub ► github.com/gordicaleksa
📚 FOLLOW ME ON MEDIUM:
Medium ► / gordicaleksa
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#graphml #graphs #deeplearning
Blog walkthrough + opinions/parallels. I'd love to hear your thoughts does this help you better understand the content of the blog? ❤ If not I won't be making these but I have to experiment hahah.
PS: sorry for the 4 sec black screen at the middle of the video - rendering went wrong. 😅
Thanks a lot for your videos on GNNs!
After scrolling through multiple papers/articles and not understanding them, I am finally starting to get some intuition on GNNs after watching your videos. And now going back to those papers, I started to actually understand them.
Thanks a lot!
Fantastic overview. You're definitely in that category of well-produced, insightful, and useful content that the recommendation systems need to be smarter in promoting.
Thank you Daven!
Love your content! Especially your highly detailed paper explanation videos, thank you for sharing your knowledge in an accessible way, cheers!
Thank you Amin! That's a great feedback I'll keep those paper review videos coming!
Great video. Very interesting with a clear presentation. Thank you so much for what you are doing.
You're welcome, thank you!
This is great. I've been thinking about fact-checking for a couple years without doing anything or searching anything about it. I didn't think about a graph "of trust" as a first step. Thanks!
Instant Subscribe.
Shakespeare wrote "Brevity is the soul of wit". What you bring to the table here is like a rich soup; food for the soul. Thank you!
Thank you!!
Your channel deserves a million subscribers, thanks for such a detailed video !
I am in a wrong niche for a million subs hahah - thanks a million!
Fantastic content. I am from social and evironmental sciences, trying to use some programming on my research work, and you opened a window for me to understand graphm. Thank you
Haven't finished the full video, but i'm surprised to hear those suggestions and thoughts about deep learning in the beginning. Pretty useful for both newcomers and intermediate researchers. They need someone to convince them about those things.
Thanks! It's a long one I know many people won't have the time to finish it 😅 and it's definitely much different compared to my paper overview videos. Lesser cognitive load. 😅
I think you have made understand graphs easier. The way you have breakdown these concepts into simple understandable pieces is mind blowing. Keep up.
Thanks man!
Awesome, I think everything is absolutely clearly explained. This could be a very exciting starting point to start lear ing about GNN!
Thank you Adrian!
Love it ！
First 2 minutes are great advice. 👍
Hvala puno na sadržaju :)
Nema na čemu!
As you always say:)), It was super super great:))
Thank you so much!
I would like to ask, do you have any tutorial for graph neural network with images? like to divide an image to regions and use each region is a node and then apply GNNs on them,?
Hello,
I have a dataset in CSV format
How do I get the following formulas (graphml - true ) for the same data set?
Did you learn all of that in two months? 19:28