Felix Opolka

CS PhD student in machine learning @Cambridge_Uni. Previously @Twitter and @TU_Muenchen.

[xiaowen dong @epomqo]

Exciting event on machine learning and signal processing on graphs in Oxford June 2023!

Please consider submitting an extended abstract by March 15th.

For more information: https://t.co/dCGbksS8Xi

#graphs #machinelearning #signalprocessing #datascience

[Felix Opolka @FelixOpo]

@yasminachami Congratulations!!🥳

[Felix Opolka @FelixOpo]

@catalinacangea Congrats again!🥳 It was such a pleasure sharing an office with you, even though of course our office chats had to be turned into walks through Cambridge in the last few months

[Shyam Tailor @satailor96]

Our proposed EGC layer is now in PyTorch Geometric.

Thanks to @rusty1s for his help and for creating this amazing library!

[Shyam Tailor @satailor96]

Join @FelixOpo and myself tomorrow at 12EST to hear more about our new work on designing efficient graph convolutions without having to trade accuracy!

[Felix Opolka @FelixOpo]

If you‘re curious how you can make GNNs more efficient and more accurate using adaptive filters drop by our poster at today‘s GNNSys workshop at #MLSys2021.

[Shyam Tailor @satailor96]

My Efficient Graph Convolutions work will be at tomorrow's GNNSys workshop at #MLSys2021. I will be at the poster session and it'll be featured in @niclane7 keynote.

Come along if you're interested in understanding how we can make efficient GNNs and still *improve* accuracy!

[Shyam Tailor @satailor96]

I am delighted to announce our new work "Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions" w/ @FelixOpo @pl219_cambridge @niclane7

We provide code + pretrained models; find our blog post here: https://t.co/Oz4vXrYGsb

[Balázs Kégl @balazskegl]

I feel angry that it is so hard to publish machine learning contributions on small data. Most problems are not images and NLP, and most data scientist work on relatively small tabular data. And most of the _value_ is there. And we know very little about that regime.

[Felix Opolka @FelixOpo]

Had such a great time recording this podcast episode for #BuildingCharacters together with @_andreeau_ 🎙Absolutely loved my internship last summer, so definitely tune in if you‘d like to hear more about being part of the #WorldWideNest!

[Brad Neuberg @bradneuberg]

Kevin Murphy’s new 2021 edition of Probabilistic Machine Learning e-textbook is out https://t.co/grB8eMAHV9

[Felix Opolka @FelixOpo]

https://t.co/XSMugstfsQ

[Felix Opolka @FelixOpo]

@guennemann Congratulations! I did the course in 2017/18 and couldn‘t have wished for a better introduction; by far my favourite module of all my studies. I’m still using the notes today to quickly brush up on topics.

[Joe Biden @JoeBiden]

America, I’m honored that you have chosen me to lead our great country.

The work ahead of us will be hard, but I promise you this: I will be a President for all Americans — whether you voted for me or not.

I will keep the faith that you have placed in me.

[Santiago @svpino]

Are you taking full advantage of Python 3?

Are you sure?

Here are 10 Python 3 features that will change the way you are writing code today.

🧵👇

[Nils Hammerla @nhammerla]

We’re looking to hire a Machine Learning Research Engineer to join the Learning Methods Research Team. In this role, you’ll take the latest ideas from research to production and make them scale! Let me know if you are interested or apply here https://t.co/sI2Vjnz4Pp

[Tiago Peixoto @tiagopeixoto]

I'm happy to announce a new project, called Netzschleuder: https://t.co/SnBeOc5Pdk

This is a network data catalogue and repository. It currently contains 257 datasets totaling 3,916 individual networks (94,956 if you include a big @openstreetmap trove).
1/5

[Hannah Fry @FryRsquared]

WHY IS THIS STILL HAPPENING

[Cătălina Cangea, PhD @catalinacangea]

Yikes.

[Leslie Berland @leslieberland]

THIS is @jack. These raw form interviews let people see who he really is, how he’s different, how he thinks, and why we’re all so incredibly grateful for him.
https://t.co/XPdw81Lbdn

[Felix Opolka @FelixOpo]

If you would like to learn more, drop by our poster at the GRL+ Workshop during poster session #1 (10.30 - 11.30 Vienna time).

[Felix Opolka @FelixOpo]

What happens if we apply graph convolutions to probabilistic rather than deterministic functions? Take a look at our paper: https://t.co/sz2QFbrauA, joint work with @pl219_Cambridge. We design a deep graph Gaussian process model, strongly outperforming neural network baselines.

[Petar Veličković @PetarV_93]

Announcing the 73 accepted papers at the GRL+ Workshop @icmlconf #icml2020!

https://t.co/iH9dtaLtYU

Further, we have nine outstanding papers on Original Research, Novel Applications and COVID-19 Applications.

Thanks to @andreeadeac22 for help with the website!

Thread below 👇