Publications de Andreas Loukas

Exploring “dark-matter” protein folds using deep learning

Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Sandrine Madeleine Suzanne Georgeon, Casper Alexander Goverde, Andreas Loukas, Stéphane Rosset, Zander Harteveld, Alexandra Krina Van Hall-Beauvais

De novo protein design explores uncharted sequence and structure space to generate novel proteins not sampled by evolution. A main challenge in de novo design involves crafting “designable” structural templates to guide the sequence searches toward adoptin ...

2024

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

Andreas Loukas, Nikolaos Karalias

Integrating functions on discrete domains into neural networks is key to developing their capability to reason about discrete objects. But, discrete domains are (I) not naturally amenable to gradient-based optimization, and (II) incompatible with deep lear ...

2022

RosettaSurf-A surface-centric computational design approach

Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Andreas Scheck, Andreas Loukas, Jaume Bonet Martinez, Stéphane Rosset, Michaël Defferrard

Proteins are typically represented by discrete atomic coordinates providing an accessible framework to describe different conformations. However, in some fields proteins are more accurately represented as near-continuous surfaces, as these are imprinted wi ...

PUBLIC LIBRARY SCIENCE2022

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

Nathanaël Perraudin, Andreas Loukas, Karolis Martinkus

We approach the graph generation problem from a spectral perspective by first generating the dominant parts of the graph Laplacian spectrum and then building a graph matching these eigenvalues and eigenvectors. Spectral conditioning allows for direct model ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Partition and Code: learning how to compress graphs

Andreas Loukas, Michael Bronstein, Nikolaos Karalias, Georgios Bouritsas

Can we use machine learning to compress graph data? The absence of ordering in graphs poses a significant challenge to conventional compression algorithms, limiting their attainable gains as well as their ability to discover relevant patterns. On the other ...

2021

Attention is not all you need: pure attention loses rank doubly exponentially with depth

Andreas Loukas, Jean-Baptiste Francis Marie Juliette Cordonnier

Attention-based architectures have become ubiquitous in machine learning. Yet, our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can be de ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021

On the Relationship between Self-Attention and Convolutional Layers

Martin Jaggi, Jean-Baptiste Francis Marie Juliette Cordonnier, Andreas Loukas

Recent trends of incorporating attention mechanisms in vision have led re- searchers to reconsider the supremacy of convolutional layers as a primary build- ing block. Beyond helping CNNs to handle long-range dependencies, Ramachandran et al. (2019) showed ...

2020

Graph Coarsening with Preserved Spectral Properties

Andreas Loukas

In graph coarsening, one aims to produce a coarse graph of reduced size while preserving important graph properties. However, as there is no consensus on which specific graph properties should be preserved by coarse graphs, measuring the differences betwee ...

ADDISON-WESLEY PUBL CO2020

What graph neural networks cannot learn: depth vs width

Andreas Loukas

This paper studies the expressive power of graph neural networks falling within the message-passing framework (GNNmp). Two results are presented. First, GNNmp are shown to be Turing universal under sufficient conditions on their depth, width, node attribut ...

2020

Dynamic Balanced Graph Partitioning

Georg Stefan Schmid, Andreas Loukas

This paper initiates the study of the classic balanced graph partitioning problem from an online perspective: Given an arbitrary sequence of pairwise communication requests between n nodes, with patterns that may change over time, the objective is to servi ...

SIAM Publications2020