no code implementations • 14 Feb 2016 • Andreas Loukas, Damien Foucard
This letter extends the concept of graph-frequency to graph signals that evolve with time.
no code implementations • 14 Feb 2016 • Elvin Isufi, Andreas Loukas, Andrea Simonetto, Geert Leus
We design a family of autoregressive moving average (ARMA) recursions, which (i) are able to approximate any desired graph frequency response, and (ii) give exact solutions for tasks such as graph signal denoising and interpolation.
no code implementations • 22 Jun 2016 • Nathanael Perraudin, Andreas Loukas, Francesco Grassi, Pierre Vandergheynst
Graph-based methods for signal processing have shown promise for the analysis of data exhibiting irregular structure, such as those found in social, transportation, and sensor networks.
no code implementations • 12 Jul 2016 • Andreas Loukas, Nathanael Perraudin
An emerging way of tackling the dimensionality issues arising in the modeling of a multivariate process is to assume that the inherent data structure can be captured by a graph.
no code implementations • 1 Nov 2016 • Andreas Loukas, Nathanaël Perraudin
This paper considers regression tasks involving high-dimensional multivariate processes whose structure is dependent on some {known} graph topology.
no code implementations • 17 Feb 2017 • Andreas Loukas
How many samples are sufficient to guarantee that the eigenvectors and eigenvalues of the sample covariance matrix are close to those of the actual covariance matrix?
no code implementations • 5 May 2017 • Francesco Grassi, Andreas Loukas, Nathanaël Perraudin, Benjamin Ricaud
An emerging way to deal with high-dimensional non-euclidean data is to assume that the underlying structure can be captured by a graph.
no code implementations • ICML 2018 • Lionel Martin, Andreas Loukas, Pierre Vandergheynst
Spectral clustering is a widely studied problem, yet its complexity is prohibitive for dynamic graphs of even modest size.
no code implementations • ICML 2017 • Andreas Loukas
How many samples are sufficient to guarantee that the eigenvectors of the sample covariance matrix are close to those of the actual covariance matrix?
no code implementations • ICML 2018 • Andreas Loukas, Pierre Vandergheynst
How does coarsening affect the spectrum of a general graph?
no code implementations • 31 Aug 2018 • Andreas Loukas
Can one reduce the size of a graph without significantly altering its basic properties?
no code implementations • 29 Jan 2019 • 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.
1 code implementation • 18 Mar 2019 • 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.
no code implementations • 23 May 2019 • Konstantinos Pitas, Andreas Loukas, Mike Davies, Pierre Vandergheynst
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.
no code implementations • 31 May 2019 • 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 nodes.
no code implementations • ICLR 2020 • Andreas Loukas
This paper studies the expressive power of graph neural networks falling within the message-passing framework (GNNmp).
1 code implementation • ICLR 2020 • Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi
This work provides evidence that attention layers can perform convolution and, indeed, they often learn to do so in practice.
Ranked #151 on Image Classification on CIFAR-10
no code implementations • NeurIPS 2020 • Andreas Loukas
A hallmark of graph neural networks is their ability to distinguish the isomorphism class of their inputs.
1 code implementation • NeurIPS 2020 • Nikolaos Karalias, Andreas Loukas
Combinatorial optimization problems are notoriously challenging for neural networks, especially in the absence of labeled instances.
1 code implementation • NeurIPS 2020 • Clement Vignac, Andreas Loukas, Pascal Frossard
We address this problem and propose a powerful and equivariant message-passing framework based on two ideas: first, we propagate a one-hot encoding of the nodes, in addition to the features, in order to learn a local context matrix around each node.
2 code implementations • 29 Jun 2020 • Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi
We also show that it is possible to re-parametrize a pre-trained multi-head attention layer into our collaborative attention layer.
no code implementations • 1 Jan 2021 • Igor Krawczuk, Pedro Abranches, Andreas Loukas, Volkan Cevher
We study the fundamental problem of graph generation.
1 code implementation • 5 Mar 2021 • Yihe Dong, Jean-Baptiste Cordonnier, Andreas Loukas
Attention-based architectures have become ubiquitous in machine learning, yet our understanding of the reasons for their effectiveness remains limited.
1 code implementation • NeurIPS 2021 • 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 dynamics.
1 code implementation • NeurIPS 2021 • Giorgos Bouritsas, Andreas Loukas, Nikolaos Karalias, Michael M. Bronstein
Can we use machine learning to compress graph data?
no code implementations • 29 Sep 2021 • Nikolaos Karalias, Joshua David Robinson, Andreas Loukas, Stefanie Jegelka
Our framework includes well-known extensions such as the Lovasz extension of submodular set functions and facilitates the design of novel continuous extensions based on problem-specific considerations, including constraints.
no code implementations • NeurIPS 2021 • 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 instance-dependent subgraphs.
1 code implementation • 4 Apr 2022 • Karolis Martinkus, Andreas Loukas, Nathanaël Perraudin, Roger Wattenhofer
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.
1 code implementation • 8 Aug 2022 • Nikolaos Karalias, Joshua Robinson, Andreas Loukas, Stefanie Jegelka
Integrating functions on discrete domains into neural networks is key to developing their capability to reason about discrete objects.
Combinatorial Optimization Vocal Bursts Intensity Prediction
no code implementations • 16 Aug 2022 • Nisha Chandramoorthy, Andreas Loukas, Khashayar Gatmiry, Stefanie Jegelka
To reduce this discrepancy between theory and practice, this paper focuses on the generalization of neural networks whose training dynamics do not necessarily converge to fixed points.
no code implementations • 19 Oct 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
Deep generative models have emerged as a popular machine learning-based approach for inverse design problems in the life sciences.
no code implementations • 21 Oct 2022 • Max W. Shen, Ehsan Hajiramezanali, Gabriele Scalia, Alex Tseng, Nathaniel Diamant, Tommaso Biancalani, Andreas Loukas
How much explicit guidance is necessary for conditional diffusion?
1 code implementation • 11 May 2023 • Max W. Shen, Emmanuel Bengio, Ehsan Hajiramezanali, Andreas Loukas, Kyunghyun Cho, Tommaso Biancalani
We investigate how to learn better flows, and propose (i) prioritized replay training of high-reward $x$, (ii) relative edge flow policy parametrization, and (iii) a novel guided trajectory balance objective, and show how it can solve a substructure credit assignment problem.
no code implementations • 5 Jun 2023 • Mattia Atzeni, Mrinmaya Sachan, Andreas Loukas
As a step towards this goal, we focus on geometry priors and introduce LatFormer, a model that incorporates lattice symmetry priors in attention masks.
1 code implementation • 8 Jun 2023 • Nathan C. Frey, Daniel Berenberg, Karina Zadorozhny, Joseph Kleinhenz, Julien Lafrance-Vanasse, Isidro Hotzel, Yan Wu, Stephen Ra, Richard Bonneau, Kyunghyun Cho, Andreas Loukas, Vladimir Gligorijevic, Saeed Saremi
We resolve difficulties in training and sampling from a discrete generative model by learning a smoothed energy function, sampling from the smoothed data manifold with Langevin Markov chain Monte Carlo (MCMC), and projecting back to the true data manifold with one-step denoising.
no code implementations • 18 Jul 2023 • Andreas Loukas, Pan Kessel
We study the generalization properties of batched predictors, i. e., models tasked with predicting the mean label of a small set (or batch) of examples.
no code implementations • NeurIPS 2023 • Karolis Martinkus, Jan Ludwiczak, Kyunghyun Cho, Wei-Ching Liang, Julien Lafrance-Vanasse, Isidro Hotzel, Arvind Rajpal, Yan Wu, Richard Bonneau, Vladimir Gligorijevic, Andreas Loukas
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences.