In this video a group of the most recent node embedding algorithms like Word2vec, Deepwalk, NBNE, Random Walk and GraphSAGE are explained by Jure Leskovec. Amazing class!
Пікірлер: 42
@sasankv99194 жыл бұрын
Watched it for the third time and now everything makes sense.
@i2005year3 жыл бұрын
15:30 Basics of deep learning for graphs 51:00 Graph Convolutional Networks 1:02:07 Graph Attention Netwirks (GAT) 1:13:57 Practical tips and demos
@sm_xiii4 жыл бұрын
Prof. Lescovec covered a lot of material in 1.5hr! It was very engaging because of his energy and teaching style.
@open_source4 жыл бұрын
;;####
@ernesttaf4 жыл бұрын
Great Sir, Congratulations for your oustanding teaching capabilities. It really change my life and my view on Graph Network. Thank you very much, Professor
@jayantpriyadarshi92664 жыл бұрын
Thank you for this lecture. Really changed my view about GCNs
@sanjaygalami3 жыл бұрын
What's the major point that strik to your head? Lets others know if it convenient for you. Thanks
@znb58733 жыл бұрын
Thank you so much for making this lecture publicly available. I have a question, is it possible to apply node embedding to dynamic graphs (temporal)? Are there any specific methods/algorithms to follow? Thanks in advance for your answer.
@gautamrajit2254 жыл бұрын
Hello. These lectures are very interesting. Would it be possible to share the GitHub repositories so that I can get a better understanding of the code involved in the implementation of these concepts?
@Olivia-wu4ve4 жыл бұрын
Awesome! Thanks for sharing. Will the hands on session be posted?
Classes so fun. The death here is different than the death in Computer Vision due to NSA death.
@MrSajjadathar4 жыл бұрын
@Machine Learning TV yes, and please share the link where you shared all the graph representation learning lectures. i will be thankful..
@eyupunlu29444 жыл бұрын
I think it is this one: kzbin.info/www/bejne/j6PLc42Lqcx6aqc
@EOh-ew2qf2 жыл бұрын
43:40 I have a question for the slide here. How can you generalize for a new node when the model learns by aggregating the neighborhoods and the new nodes doesn't have a neighborhood yet.
@vgreddysaragada Жыл бұрын
Great work..
@alvin54244 жыл бұрын
Any plans to publish lectures 17, 18 and 19?
@MachineLearningTV4 жыл бұрын
Yep! Soon we will upload new lectures!
@eugeniomarinelli11043 жыл бұрын
where do I find the slides fo this lecture
@kanishkmair29204 жыл бұрын
In GCN, we get a single output. In GraphSAGE you concatenate it to keep the info separate. So at each step, the output H^k will have 2 outputs, isn't it? If not, then how are they aggregated and still kept separate
@paulojhonny43644 жыл бұрын
Kanishk Mair hi, I didn’t understand either. Did you find anything about it?
@kanishkmair29204 жыл бұрын
I tried to work on pytorch geometric using it (SAGEConv). Not sure how it works but looking at it's source code might help
@sm_xiii4 жыл бұрын
I think the concatenated output is the embedding of the target node. And it depends on the downstream task to further process it, by passing it through more layers, before having the final output.
@ShobhitSharmaMTAI3 жыл бұрын
My question at 31:00, what if previous layer embedding of same node is not multiply with Bk like Bk hv(k-1)...what will be the impact on embedding...
Deeper networks will not always be more powerful as you may lose vector features in translation .And due to additional weight matrices the neural networks will be desensitized to feature input.Number of hidden layers should not be greater than input dimension.
@MrSajjadathar4 жыл бұрын
Sir can you please share Tuesday lecture
@MachineLearningTV4 жыл бұрын
The past Tuesday?
@MrSajjadathar4 жыл бұрын
@@MachineLearningTV yes, and please share the link where you shared all the graph representation learning lectures. i will be thankful..
@MachineLearningTV4 жыл бұрын
It is available now. Check the new video
@deweihu10033 жыл бұрын
On behalf a people from a remote eastern country: niubi!!!!
@phillipneal81944 жыл бұрын
How do you aggregate dissimilar features ? For example sex, temperature, education level for each node ?
@이혜경-y8x4 жыл бұрын
Where can I get slides?
@ducpham99914 жыл бұрын
you can find it at here web.stanford.edu/class/cs224w/
@kognitiva3 жыл бұрын
kzbin.info/www/bejne/bXuofYtsec6IrrM "what we would like to do is here input the graph and over here good predictions will come" Yes, that is exactly it! xD
@jcorona4755 Жыл бұрын
Pagan porque vean que tiene más seguidores. De echo pagas $10 pesos por cada video