Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences


Oct 19, 2022
Nataša Tagasovska, Nathan C. Frey, Andreas Loukas, Isidro Hötzel, Julien Lafrance-Vanasse, Ryan Lewis Kelly, Yan Wu, Arvind Rajpal, Richard Bonneau, Kyunghyun Cho, Stephen Ra, Vladimir Gligorijević

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On the generalization of learning algorithms that do not converge


Aug 19, 2022
Nisha Chandramoorthy, Andreas Loukas, Khashayar Gatmiry, Stefanie Jegelka

Add code

* 27 pages, under review 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions


Aug 08, 2022
Nikolaos Karalias, Joshua Robinson, Andreas Loukas, Stefanie Jegelka

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SPECTRE : Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators


Apr 04, 2022
Karolis Martinkus, Andreas Loukas, Nathanaël Perraudin, Roger Wattenhofer

Add code

* 20 pages, 10 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning


Oct 27, 2021
Mattia Atzeni, Jasmina Bogojeska, Andreas Loukas

Add code

* NeurIPS 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Partition and Code: learning how to compress graphs


Jul 05, 2021
Giorgos Bouritsas, Andreas Loukas, Nikolaos Karalias, Michael M. Bronstein

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

What training reveals about neural network complexity


Jun 08, 2021
Andreas Loukas, Marinos Poiitis, Stefanie Jegelka

Add code

* 31 pages, 8 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth


Mar 05, 2021
Yihe Dong, Jean-Baptiste Cordonnier, Andreas Loukas

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Building powerful and equivariant graph neural networks with structural message-passing


Jul 11, 2020
Clement Vignac, Andreas Loukas, Pascal Frossard

Add code

* Submitted to Neurips 2020. 18 pages, 5 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Multi-Head Attention: Collaborate Instead of Concatenate


Jun 29, 2020
Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>