Logo

TSB FGML5G's Personal Meeting Room - Shared screen with speaker view
Sujan Shrestha
01:01:10
Good Evening from Nepal
02_Sisay Tadesse Arzo(DISI)
01:02:12
Yes I am
Mustapha
01:02:17
You're on mute Mr. Reinhard, I can't hear you
Charles Ssengonzi
01:02:28
Yes
02_Sisay Tadesse Arzo(DISI)
01:02:33
Yes I am I am from Trento, Italy
Charles Ssengonzi
01:02:44
Calling in from Johannesburg
د.حسن أبو سعدة
01:02:45
Good evening from Egypt
Sameer Srivastava
01:02:48
from New Delhi, India
jfb
01:02:48
Yes. Hi, I am from Colombia.
dzamzam
01:02:51
yes I want to participate (Egypt)
saeedeh parsaeefard
01:02:59
From Toronto
Asit kadayan
01:02:59
calling from new delhi india
mruthyunjaykori
01:03:57
Best wishes for PhD defence!
Charles Ssengonzi
01:04:30
Best wishes in your defense
02_Sisay Tadesse Arzo(DISI)
01:04:44
Yes
Charles Ssengonzi
01:04:51
Yes
jfb
01:05:20
Is this webminar being recorded?
Vishnu
01:05:58
yes, it is recorded
Vishnu
01:07:20
We take questions here. Please feel free to put your questions here.
Prof. Thanuja
01:09:00
Hi . This is Prof. Thanuja. Professor, Karnataka India
Abdulaziz Binsaif
01:10:00
hi, this is Abdulaziz Binsaif from Saudi Telecom Company,Saudi Arabia
Vishnu
01:10:00
welcome.
Thomas Basikolo (ITU)
01:15:16
Please Register for the ITU AI/ML in 5G Challenge here: https://www.itu.int/net4/CRM/xreg/web/Registration.aspx?Event=C-00007607
Thomas Basikolo (ITU)
01:15:52
Join our Slack Channel to keep updated: https://join.slack.com/t/itu-challenge/shared_invite/zt-eql00z05-CXelo7_aL0nHGM7xDDvTmA
JORGE MARTIN PEREZ
01:20:50
I've read that when you change the underlying graph, the GNNs eigenfunctions change as well. How can your GNNs generalize to "unseen" networks?
JORGE MARTIN PEREZ
01:22:55
As well I've read that operational backward and forward pass operations take O(n^2), whilst traditional CNNs have O(n). Why do you state that GNNs are faster?
FMekuria
01:23:50
Networks are also based on regulatory & standards guidelines, how do you build that in the GNN ?
Simon
01:36:19
Could you please share the slides with us through email?Could you please provide a pytorch version of RouteNet? Now pytorch is widely used.
Thomas Basikolo (ITU)
01:37:15
The Slides can be obtained on the ITU AI/ML in 5G Challenge: https://www.itu.int/en/ITU-T/AI/challenge/2020/Pages/default.aspx
Thomas Basikolo (ITU)
01:37:46
Presentation slides: https://www.itu.int/en/ITU-T/AI/challenge/2020/Documents/Presentation_gnnet_challenge.pdf
02_Sisay Tadesse Arzo(DISI)
01:38:48
I don't know if this is appropriate to ask here. I was trying to run the RouteNet using the main.py code that you provided to see the first test. I get the following problems. I am new to RNN and ML. "... 2020-06-19 14:25:22.119924: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version2020-06-19 14:25:22.129538: F tensorflow/stream_executor/lib/statusor.cc:34] Attempting to fetch value instead of handling error Internal: failed to get device attribute 13 for device 0: CUDA_ERROR_UNKNOWN: unknown error"
02_Sisay Tadesse Arzo(DISI)
01:39:19
I mean new GNN
Thomas Basikolo (ITU)
01:39:30
We can discuss the finer details in the Slack Channel
Thomas Basikolo (ITU)
01:41:12
https://join.slack.com/t/itu-challenge/shared_invite/zt-eql00z05-CXelo7_aL0nHGM7xDDvTmA
FAYAZ Ahamed
01:44:29
Whats the future of GNN in next 10 years especially In health industry
JORGE MARTIN PEREZ
01:46:26
But if you build a kernel filter to act on the "frequency domain", the frequencies, i.e., the laplacian eigenfunction changes.Thus, the learned filter does not apply to the new graph.
Loïck Bonniot
01:49:05
Hi, thanks for the presentation! Would you be able to provide RouteNet baseline predictions for training and validation dataset? Thanks
JAIME VERGARA TEJADA
01:49:37
Maybe I missed a part of your explanI was checking the training dataset, but I cannot see a relation between the simulation results and the queueing policy implemented. Each .tar.gz has the results of one policy on all the nodes?
JAIME VERGARA TEJADA
01:50:54
And the MAPE will be measured according to each pair end-to-end delay?
Fathi Abdeldayem
01:51:23
can we have the presentation please
Thomas Basikolo (ITU)
01:51:59
Presentation slides:https://www.itu.int/en/ITU-T/AI/challenge/2020/Documents/Presentation_gnnet_challenge.pdf
Fathi Abdeldayem
01:52:47
from your experience what are the value proposition of 5G ML from an operator prespective please
JAIME VERGARA TEJADA
01:56:12
Maybe I missed a part of your explanation. I was checking the training dataset, but I cannot see a relation between the simulation results and the queueing policy implemented. Each .tar.gz has the results of one policy on all the nodes?
Fathi Abdeldayem
01:57:00
yes please we are very interested from Network prespective
Thomas Basikolo (ITU)
01:58:07
ai5gchallenge@itu.int
Charles Ssengonzi
01:58:50
Thanks
Thomas Basikolo (ITU)
01:59:28
Join us on the Slack Channelhttps://join.slack.com/t/itu-challenge/shared_invite/zt-eql00z05-CXelo7_aL0nHGM7xDDvTmA
Vishnu
01:59:37
The questions that I missed, we will get back via email or slack. Sorry!