activity
20162022
most citedOn the Relationship between Self-Attention and Convolutional Layers

89 citations · 113 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

16 papers · 1 filter

cs.LG20221 cited

Conditional Diffusion with Less Explicit Guidance via Model Predictive Control

Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia +4

How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guida…

cs.LG20224 cited

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

Nataša Tagasovska, Nathan C. Frey, Andreas Loukas +9

Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences. However, these problems often require sampling ne…

cs.LG2021

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

Mattia Atzeni, Jasmina Bogojeska, Andreas Loukas

State-of-the-art approaches to reasoning and question answering over knowledge graphs (KGs) usually scale with the number of edges and can only be applied effectively on small inst…

cs.LG20212 cited

What training reveals about neural network complexity

Andreas Loukas, Marinos Poiitis, Stefanie Jegelka

This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training d…

cs.LG2020

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

Clement Vignac, Andreas Loukas, Pascal Frossard

Message-passing has proved to be an effective way to design graph neural networks, as it is able to leverage both permutation equivariance and an inductive bias towards learning lo…

cs.LG2020

Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs

Nikolaos Karalias, Andreas Loukas

Combinatorial optimization problems are notoriously challenging for neural networks, especially in the absence of labeled instances. This work proposes an unsupervised learning fra…