Hi all

Hello everyone, Dr Naranmandakh T, Greetings from the Communications Regulatory Commission of Mongolia,

Welcome :)

Hellow Vishnue;

Reinhard Geneva

Hello everyone from Nairobi, Kenya

Geneva, Switzerland

Mumbai,India

New Delhi, India

Kind regards from Germany

Berlin, Germany

Hello from Brazil, Belem

Barcelona, Spain

Tokyo Japan

Bangalore, India

Vannes, France

Munich Germany

Belem, Brazil

Bangalore, India

Dia Duit (Hello) from Donegal, Ireland :)

Johannesburg South Africa

Hello everyone! Linköping, Sweden

Kingston, Canada

London, UK

Hi, attending from Tokyo, Japan:-)

Barcelona, Spain

Riyadh, Saudi Arabia

Pittsburgh, Pennsylvania USA

Recife, Brazil

Shagufta, LYIT, Ireland

Maryland USA

Hi, attending from Osaka, Japan

Hello from Cairo, Egypt.

Geneva

Mohammad Abid, stc, Riyadh, Saudi Arabia

Okinawa, Japan

Paris

Willy from Indonesia

Greeting to all -MP Singhal New Delhi IndiIa

Beijing, China

Barcelona, Spain

Hello from Okinawa Japan.

Geneva, Switzerland ;)

Guizhou, China. :)

London

china

Greetings form Istanbul

St.-Petersburg, Russia

https://www.itu.int/en/ITU-T/AI/challenge/2020/Pages/PROGRAMME.aspx

With which product did you compare yours ? do have any results?

I have a follow on question to vishunu

Do you have any justification why MLP is giving you the worst performance among all the predictors used? could it be due to manual feature refinement and reduction carried out?

why Tree model work better than MLP and SVM in this problem?

p0[

Any reason why the recall of your trained model is low?

the GCN model specifically

why GCN performs better than other models, can you explain based on the problem

how we can get the slides of this event.

The slides and information can be found on the website

What kind of environment did you use to test your solution?.. simulation?.. real network deployment?

Also when you say traffic prediction.. do you mean the overall traffic on the network?

What is the type of nodes in your scenario here (in the context of 5G)? and is it practically easy to introduce these changes to the topology?

that was wonderful , for 44.5% improvement simulation , what was the duration of data what was taken into consideration?

questions: 1. how much % energy saving will be achieved from this approach?. 2. any sensor input considered as data source?. 3. what all data inputs expected for this approach?

answer for question 1:We don't know how much energy saving because we just have the data of everyday's energy-saving status.

answer for question 2:We have no access to real-time data source. If sensor input is offline, we should have considered.

answer for question 3:Historical base station performance data, historical energy saving status and base station configuration information.

Mr. Ming: is there a relation with standards?

What kind of algorithms are used for the orchestration?

@Thomas when will we know results of public voting

The results will be announced on Thursday

thanks

Did you consider evaluating the cost of the communication overhead added by applying federated learning?and also from the aspect of practicality, will these distributed devices be able to carry out the local training tasks? as in most of the federated learning cases the training task is simpler than the one in your work!

no problem!

Thank you Ahmad

For NU Huskies: Do U have results for infusing two out of three of the modalities (image, lidar, coordinates)? How would a network infusing only LIDAR and coordinate data work? How can you be sure that your proposed detection and background removal on image data is actually the reason for improvements  in the final result when 3 modalities are infused? Do U have an ablation study to show contribution of your proposed detection and background removal on the final performance given the fact that it increases the complexity of NN significantly? 

For Participants in The ITU AI/ML in 5G Challenge, please respond to this survey: https://forms.office.com/Pages/ResponsePage.aspx?id=12TkI-YEh0uRPCS9iSGf0-yqkfLCoQ9IpTbc_XELf95URExJWlM2OExXVEQ5VFhFSTUzWUU3SDU1WS4u

maybe some training packet could be dropped to reduce communication overhead because ML training load distribution has long tail. Removing some redundant training data may not impact the final performance of ML training.

The Grand Challenge Finale (Keynotes + Awards) will take place on 17 Dec. Please register here: https://itu.zoom.us/webinar/register/WN_bm4oJ_OeRH-Ilnb4GY_gMQ

For NU Huskies: Do U have results for infusing two out of three of the modalities (image, lidar, coordinates)? How would a network infusing only LIDAR and coordinate data work? How can you be sure that your proposed detection and background removal on image data is actually the reason for improvements  in the final result when 3 modalities are infused? Do U have an ablation study to show contribution of your proposed detection and background removal on the final performance given the fact that it increases the complexity of NN significantly? 

If fc layer can be replaced by other opertaion such as average pool or 1*1 conv to reduce complexity of NN ? because fc(fully connection layer) may have so many parameters. My opinion..

When is the next challenge?

Please tune-in (join) in 17 Dec to get information about what happens next: https://itu.zoom.us/webinar/register/WN_bm4oJ_OeRH-Ilnb4GY_gMQ

For BeamSoup: What is beta in your loss function? Did you analyse the impact of beta by some ablation? It seems like such loss should force your outputs to two different distributions (one hot encoded best beam vs. signal power), can you please elaborate on that a bit?

Beam soup: The way the baseline pre-process LIDAR data at the front end includes embedding the coordinate data into the LIDAR input. I am worried that separately infusing coordinate data may be adding unnecessary complexity to the NN architecture and even destructive in non line of sight (NLOS) cases? 

Congratulations again to all participants of the PS-012 [beam-selection]! Great job!

Of course, great job!

Thank you Aldebaro and your team for providing the Raymobtime dataset.

An lso for posing this Nice idea in the first place Aldebaro. Would be nice to collaborate to publish an overview kind of paper on this topic putting together achievements from all teams on the competition and your results of course.

Tomorrow 15:30- 15:35 (CET), Call for papers: Ian Akyildiz, Editor-in-Chief, Special issue of ITU Journal on Future and Evolving Technologies (ITU J-FET)​): “AI/ML Solutions in 5G and Future Networks”

17 Dec 15:30- 15:35 (CET), Call for papers: Ian Akyildiz, Editor-in-Chief, Special issue of ITU Journal on Future and Evolving Technologies (ITU J-FET)​): “AI/ML Solutions in 5G and Future Networks”

as far as I understand you are using some parameters to predict current throughput value,if so, did you consider predicting future throughput values and not the current ones based on historical data? (time series forecasting I mean)

Are the presentations available?

The presentations are available on the website: https://www.itu.int/en/ITU-T/AI/challenge/2020/Pages/PROGRAMME.aspx

Nice talk! May I ask what kind of aggregations you used in graph convolutions?

what is the range of throughput values here?to get a sense of the RMSE!

I cannot speak right now, but what is the computational complexity of GCN? compared to CNN?

Regarding Loïck's question, I leave here an interesting paper that includes a comprehensive evaluation of different aggregation functions in GNN/GCN: https://arxiv.org/pdf/2004.05718.pdf

We will continue tomorrow with presentations from various problem statements: https://www.itu.int/en/ITU-T/AI/challenge/2020/Pages/PROGRAMME.aspx

For Participants in The ITU AI/ML in 5G Challenge, please respond to this survey:https://forms.office.com/Pages/ResponsePage.aspx?id=12TkI-YEh0uRPCS9iSGf0-yqkfLCoQ9IpTbc_XELf95URExJWlM2OExXVEQ5VFhFSTUzWUU3SDU1WS4uThe Grand Challenge Finale (Keynotes + Awards) will take place on 17 Dec.Please register here: https://itu.zoom.us/webinar/register/WN_bm4oJ_OeRH-Ilnb4GY_gMQ

R

will the recording be shared by any chance?

I vote to last team

thank you!

Yes, recording will be available.

bye

bye bye

OK great.. thanks Vishnu! :))

Looking forward to receiving the recording. Thank you

bye