Johannes Brandstetter   @jo_brandstetter

Tenure Track Researcher at JKU Linz, currently ELLIS PostDoc at University of Amsterdam





  Tweets by Johannes Brandstetter  

Johannes Brandstetter    @jo_brandstetter   ·   10/7/2021
Are you interested in graph structured data? Do you want to include geometry and physics to boost your GNNs? Check out our paper on Steerable E(3) Equivariant Graph Neural Networks. Joint work with @robdhess @ElisevanderPol @erikjbekkers @wellingmax https://t.co/exBcDhQ44k
 
 Reply      Retweet   50      Like     188    

More by:   Johannes Brandstetter
zoom in  
 



Johannes Brandstetter    @jo_brandstetter   ·   10/7/2021
SEGNNs can be interpreted as generalization of equivariant graph networks. Node and edge attributes are not restricted to invariant scalars, but can also be vectors or tensors now. 4/6
 Reply      Retweet        Like     3    

More by:   Johannes Brandstetter
zoom in  
 



Johannes Brandstetter    @jo_brandstetter   ·   10/7/2021
Through the lens of equivariant nonlinear convolutions, successful components of SEGNNs are exposed: (i) non-linear message aggregation improves classic linear (steerable) point convolutions; (ii) steerable messages improve recent equivariant networks that send invariant messages
 Reply      Retweet        Like     3    

More by:   Johannes Brandstetter
zoom in  
 



Johannes Brandstetter    @jo_brandstetter   ·   10/7/2021
SEGNNs provide a new class of update activation functions for general use with steerable feature fields, which allow the incorporation of geometric and physical quantities into the node updates. 2/6
 Reply      Retweet        Like     3    

More by:   Johannes Brandstetter
zoom in  
 









  More from:  



Jian Tang
Assistant Professor at Mila. Working on deep learning for graphs with applications in knowledge graphs, Drug Discovery and material discovery.

Peter Battaglia
Research Scientist, DeepMind

Quanta Magazine
Big ideas in science and math. Because you want to know more. Launched by @SimonsFdn. https://t.co/n6itBXqN3A Get our weekly newsletter: https://t.co/XI6i48Zcdk

Sebastian Raschka
Author of the 'Python Machine Learning' book. Tweet about Python, deep learning research, open source. Asst Prof of Statistics @UWMadison. Opinions are my own.

Simone Scardapane
I fall in love with a new #machinelearning topic every month 🙄 Researcher @SapienzaRoma | Chairman @iaml_it | Co-host @SmarterPodcast | @GoogleDevExpert