Uploaded June 2021 | Updated September 2026, 1 week ago
❤️ Become The AI Epiphany Patreon ❤️ ► patreon.com/theaiepiphany
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Paper: Do Transformers Really Perform Bad for Graph Representation?
In this video, I cover Graphormer a new transformer model that achieved SOTA results on the OGB large-scale challenge benchmark.
It achieved that by introducing 3 novel types of structural biases/encodings into the classic transformer encoder.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: arxiv.org/abs/2106.05234
✅ What can GNNs learn blog: https://andreasloukas.blog/2019/12/27/what-gnn-can-and-cannot-learn/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Key points of the paper
02:15 Graph-level predictions and why we need structural information
05:35 GNNs basics
09:40 Centrality encoding explained in depth
14:15 Spatial encoding explained in depth
18:00 Edge encoding explained in depth
22:30 Results on OGB LSC
23:30 Graphormer handles over-smoothing
25:10 Other results and ablation study
28:20 Graphormer is more expressive than WL
30:30 Mean aggregation as a special case of Graphormer
35:00 Sum aggregation as a special case of Graphormer
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 ► patreon.com/theaiepiphany
One-time donation:
paypal.com/paypalme/theaiepiphany
Much love! ❤️
Huge thank you to these AI Epiphany patreons:
Petar Veličković
Zvonimir Sabljic
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💡 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 ► linkedin.com/in/aleksagordic
Twitter ► twitter.com/gordic_aleksa
Instagram ► instagram.com/aiepiphany
Facebook ► facebook.com/aiepiphany
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► discord.gg/peBrCpheKE
📢 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.medium.com
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#graphormer #graphs #transformers
❤️ Become The AI Epiphany Patreon ❤️ ► patreon.com/theaiepiphany
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
Paper: Do Transformers Really Perform Bad for Graph Representation?
In this video, I cover Graphormer a new transformer model that achieved SOTA results on the OGB large-scale challenge benchmark.
It achieved that by introducing 3 novel types of structural biases/encodings into the classic transformer encoder.
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: arxiv.org/abs/2106.05234
✅ What can GNNs learn blog: https://andreasloukas.blog/2019/12/27/what-gnn-can-and-cannot-learn/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00 Key points of the paper
02:15 Graph-level predictions and why we need structural information
05:35 GNNs basics
09:40 Centrality encoding explained in depth
14:15 Spatial encoding explained in depth
18:00 Edge encoding explained in depth
22:30 Results on OGB LSC
23:30 Graphormer handles over-smoothing
25:10 Other results and ablation study
28:20 Graphormer is more expressive than WL
30:30 Mean aggregation as a special case of Graphormer
35:00 Sum aggregation as a special case of Graphormer
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 ► patreon.com/theaiepiphany
One-time donation:
paypal.com/paypalme/theaiepiphany
Much love! ❤️
Huge thank you to these AI Epiphany patreons:
Petar Veličković
Zvonimir Sabljic
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💡 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 ► linkedin.com/in/aleksagordic
Twitter ► twitter.com/gordic_aleksa
Instagram ► instagram.com/aiepiphany
Facebook ► facebook.com/aiepiphany
👨👩👧👦 JOIN OUR DISCORD COMMUNITY:
Discord ► discord.gg/peBrCpheKE
📢 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.medium.com
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#graphormer #graphs #transformers
![DALL-E mini explained | min(DALL-E) | Craiyon | ML Coding Series
❤️ Become The AI Epiphany Patreon ❤️
https://www.patreon.com/theaiepiphany
👨👩👧👦 Join our Discord community 👨👩👧👦
https://discord.gg/peBrCpheKE
In the 6th video of the ML coding series I start explaining the DALL-E mini project - the open-source implementation of DALL-E. I start with its minimal port into PyTorch called min(DALL-E).
I first give you the necessary context by walking you through the VQ-GAN, BART, GLU, and DALL-E papers as well as the Weights & Biases report on DALL-E mini, and then I dig into the actual code!
Let me know how you like this video!
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ min-dalle code: https://github.com/kuprel/min-dalle
My previous relevant videos:
✅ VQ-GAN: https://www.youtube.com/watch?v=j2PXES-liuc
✅ VQ-VAE: https://www.youtube.com/watch?v=VZFVUrYcig0
✅ DALL-E: https://www.youtube.com/watch?v=jMqLTPcA9CQ
✅ Weights & Biases DALL-E mini report: https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-Mini-Explained-with-Demo Vmlldzo4NjIxODA
✅ Rivers Have Wings tweet: https://twitter.com/RiversHaveWings/status/1478093658716966912
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
⌚️ Timetable:
00:00:00 Intro
00:02:12 VQGAN overview
00:08:42 Conditioning in VQGAN
00:14:00 BART transformer
00:18:25 DALL-E 1 overview
00:24:13 DALL-E mini Weights & Biases report
00:30:35 [code] min-dalle
00:34:23 Text tokenizer
00:41:50 BART encoder
00:44:22 GLU explained (paper + code)
00:51:22 BART decoder
00:58:35 Image latent vector autoregressive generation
01:05:10 Super conditioning, top-k sampling
01:09:53 VQGAN decoder
01:15:05 Outro
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 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 - https://www.patreon.com/theaiepiphany
One-time donation - https://www.paypal.com/paypalme/theaiepiphany
Huge thank you to these AI Epiphany patreons:
Eli Mahler
Petar Veličković
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💼 LinkedIn - https://www.linkedin.com/in/aleksagordic/
🐦 Twitter - https://twitter.com/gordic_aleksa
👨👩👧👦 Discord - https://discord.gg/peBrCpheKE
📺 YouTube - https://www.youtube.com/c/TheAIEpiphany/
📚 Medium - https://gordicaleksa.medium.com/
💻 GitHub - https://github.com/gordicaleksa
📢 AI Newsletter - https://aiepiphany.substack.com/
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
#dallemini #imagesynthesis #mindalle DALL-E mini explained | min(DALL-E) | Craiyon | ML Coding Series](https://i.ytimg.com/vi/x_8uHX5KngE/mqdefault.jpg)






