GAT: Graph Attention Networks (Graph ML Research Paper Walkthrough)
#attention #graphml #machinelearning
⏩ Abstract: We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved state-of-the-art results across three established transductive and inductive graph benchmarks: the Cora and Citeseer citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs are entirely unseen during training).
Sign-up for Email Subscription - https://forms.gle/duSwrYAGw6zUhoGf9
Graph Machine Learning Playlist: https://www.youtube.com/watch?v=-uJL_ANy1jc&list=PLsAqq9lZFOtU7tT6mDXX_fhv1R1-jGiYf
⏩ OUTLINE:
0:00 - Abstract and Background
02:37 - Understanding Graph Attention Layer - Theory, Equations
⏩ Paper Title: Graph Attention Networks
⏩ Paper: https://arxiv.org/abs/1710.10903v1
⏩ Author: Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio
⏩ Organisation: University of Cambridge, UAB, Montreal Institute for Learning Algorithms
Please feel free to share out the content and subscribe to my channel :)
⏩ Subscribe - https://youtube.com/channel/UCoz8NrwgL7U9535VNc0mRPA?sub_confirmation=1
**********************************************
If you want to support me financially which is totally optional and voluntary ❤️
You can consider buying me chai ( because I don't drink coffee :) ) at https://www.buymeacoffee.com/TechvizCoffee
❤️ Support using Paypal - https://www.paypal.com/paypalme/TechVizDataScience
**********************************************
⏩ Youtube - https://www.youtube.com/c/TechVizTheDataScienceGuy
⏩ LinkedIn - https://linkedin.com/in/prakhar21
⏩ Medium - https://medium.com/@prakhar.mishra
⏩ GitHub - https://github.com/prakhar21
⏩ Twitter - https://twitter.com/rattller
*********************************************
Tools I use for making videos :)
⏩ iPad - https://tinyurl.com/y39p6pwc
⏩ Apple Pencil - https://tinyurl.com/y5rk8txn
⏩ GoodNotes - https://tinyurl.com/y627cfsa
#techviz #datascienceguy #representation #research #graphs
About Me:
I am Prakhar Mishra and this channel is my passion project. I am currently pursuing my MS (by research) in Data Science. I have an industry work-ex of 3 years in the field of Data Science and Machine Learning with a particular focus on Natural Language Processing (NLP).
Видео GAT: Graph Attention Networks (Graph ML Research Paper Walkthrough) канала TechViz - The Data Science Guy
⏩ Abstract: We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved state-of-the-art results across three established transductive and inductive graph benchmarks: the Cora and Citeseer citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs are entirely unseen during training).
Sign-up for Email Subscription - https://forms.gle/duSwrYAGw6zUhoGf9
Graph Machine Learning Playlist: https://www.youtube.com/watch?v=-uJL_ANy1jc&list=PLsAqq9lZFOtU7tT6mDXX_fhv1R1-jGiYf
⏩ OUTLINE:
0:00 - Abstract and Background
02:37 - Understanding Graph Attention Layer - Theory, Equations
⏩ Paper Title: Graph Attention Networks
⏩ Paper: https://arxiv.org/abs/1710.10903v1
⏩ Author: Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio
⏩ Organisation: University of Cambridge, UAB, Montreal Institute for Learning Algorithms
Please feel free to share out the content and subscribe to my channel :)
⏩ Subscribe - https://youtube.com/channel/UCoz8NrwgL7U9535VNc0mRPA?sub_confirmation=1
**********************************************
If you want to support me financially which is totally optional and voluntary ❤️
You can consider buying me chai ( because I don't drink coffee :) ) at https://www.buymeacoffee.com/TechvizCoffee
❤️ Support using Paypal - https://www.paypal.com/paypalme/TechVizDataScience
**********************************************
⏩ Youtube - https://www.youtube.com/c/TechVizTheDataScienceGuy
⏩ LinkedIn - https://linkedin.com/in/prakhar21
⏩ Medium - https://medium.com/@prakhar.mishra
⏩ GitHub - https://github.com/prakhar21
⏩ Twitter - https://twitter.com/rattller
*********************************************
Tools I use for making videos :)
⏩ iPad - https://tinyurl.com/y39p6pwc
⏩ Apple Pencil - https://tinyurl.com/y5rk8txn
⏩ GoodNotes - https://tinyurl.com/y627cfsa
#techviz #datascienceguy #representation #research #graphs
About Me:
I am Prakhar Mishra and this channel is my passion project. I am currently pursuing my MS (by research) in Data Science. I have an industry work-ex of 3 years in the field of Data Science and Machine Learning with a particular focus on Natural Language Processing (NLP).
Видео GAT: Graph Attention Networks (Graph ML Research Paper Walkthrough) канала TechViz - The Data Science Guy
Показать
Комментарии отсутствуют
Информация о видео
23 сентября 2021 г. 8:46:43
00:08:45
Другие видео канала
Chain of thought Prompting in Large Language Models #shortsOCR-VQA: Visual Question Answering by Reading Text in Images (Research Paper Summary)An Efficient System for Grammatical Error Correction on Mobile Devices (Research Paper Walkthrough)Techniques for getting Graph Embeddings from Node Embeddings (Graph Machine Learning Concept)BLEURT: Learning Robust Metrics for Text Generation (Research Paper Walkthrough)Adapt LLMs on your Task #aiGlobal Attention Vs Local Attention #shortsTop Features for Movie Recommendation #recommendersystemsAuto Generating Python code by editing Spreadsheet using MitoWhat is Maximal Margin Relevance?API Design - 3 common Pagination StrategiesOn Generating Extended Summaries of Long Documents (Research Paper Walkthrough)Advanced Chucking Strategy for RAG #llms #aiTraining & Production Performance Mismatch in MLEx2: Neural Data Augmentation via Example Extrapolation (Research Paper Walkthrough)Detecting Hallucinated Content in Conditional Neural Sequence Generation (NLP Paper Walkthrough)THANK YOU FOR YOUR SUPPORT SO FAR #MyYearOnYouTube 2021HARP: Hierarchical Representation Learning for Network | ML with Graphs (Research Paper Walkthrough)Improving RAG performance with Parent Context RetrieverTraining Question Answering Models From Synthetic Data (Research Paper Walkthrough)Aspect-based Document Similarity for Research Papers (Research Paper Walkthrough)