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 2019Show all

6 papers · 1 filter

cs.LG201989 cited

On the Relationship between Self-Attention and Convolutional Layers

Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi

Recent trends of incorporating attention mechanisms in vision have led researchers to reconsider the supremacy of convolutional layers as a primary building block. Beyond helping C…

cs.LG2019

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 Turin…

cs.LG201911 cited

Discriminative structural graph classification

Younjoo Seo, Andreas Loukas, Nathanaël Perraudin

This paper focuses on the discrimination capacity of aggregation functions: these are the permutation invariant functions used by graph neural networks to combine the features of n…

cs.LG2019

The role of invariance in spectral complexity-based generalization bounds

Konstantinos Pitas, Andreas Loukas, Mike Davies +1

Deep convolutional neural networks (CNNs) have been shown to be able to fit a random labeling over data while still being able to generalize well for normal labels. Describing CNN…

cs.LG2019

Extrapolating paths with graph neural networks

Jean-Baptiste Cordonnier, Andreas Loukas

We consider the problem of path inference: given a path prefix, i.e., a partially observed sequence of nodes in a graph, we want to predict which nodes are in the missing suffix. I…

cs.LG20191 cited

Approximating Spectral Clustering via Sampling: a Review

Nicolas Tremblay, Andreas Loukas

Spectral clustering refers to a family of unsupervised learning algorithms that compute a spectral embedding of the original data based on the eigenvectors of a similarity graph. T…