Recherche

Afficher tous les résultats pour

Accueil

Publication

Multilayer Graph Clustering With Optimized Node Embedding

À propos
Confidentialité
Mentions légales

Graph Chatbot

Publications associées (55)

Page 2 sur 3

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Scott William Pesme, Hristo Georgiev Papazov

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Diffusion Stochastic Optimization for Min-Max Problems

Ali H. Sayed, Haoyuan Cai

The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of O(ϵ-2) to achieve an ϵ-stationary solut ...

2025

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

The topology of a chaotic attractor in the Kuramoto-Sivashinsky equation

Tobias Schneider, Pierre Beck

The Birman-Williams theorem gives a connection between the collection of unstable periodic orbits (UPOs) contained within a chaotic attractor and the topology of that attractor, for three-dimensional systems. In certain cases, the fractal dimension of a ch ...

2025

On the Generalization of Stochastic Gradient Descent with Momentum

Volkan Cevher, Kimon Antonakopoulos

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Microtome Publishing2024

A Reconfigurable High-Dynamic Range ∆Σ Front-End with Event-Based Decimation for Bandwidth-Efficient Implantable Neural Interfaces

David Atienza Alonso, Giovanni Ansaloni, Pasquale Davide Schiavone, Juan Pablo Sapriza Araujo

As the demand for high channel counts and high-resolution recordings of neural activity continues to grow, the increased power and data rate generated impose hard constraints on the telemetry capabilities of wireless implantable neural interfaces. To addre ...

IEEE2025

Equivariant Neural Architectures for Representing and Generating Graphs

Clément Arthur Yvon Vignac

Graph machine learning offers a powerful framework with natural applications in scientific fields such as chemistry, biology and material sciences. By representing data as a graph, we encode the prior knowledge that the data is composed of a set of entiti ...

EPFL2023

Image steganalysis using active learning and hyperparameter optimization

Zaffar Ahmed Shaikh

Image steganalysis, detecting hidden data in digital images, is essential for enhancing digital security. Traditional steganalysis methods typically rely on large, pre-labeled image datasets, which are difficult and costly to compile. To address this, this ...

Springer Science and Business Media LLC2025

A full characterization of invariant embeddability of unimodular planar graphs

Laszlo Marton Toth

When can a unimodular random planar graph be drawn in the Euclidean or the hyperbolic plane in a way that the distribution of the random drawing is isometry-invariant? This question was answered for one-ended unimodular graphs in Benjamini and Timar, using ...

WILEY2023

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models

Philippe Schwaller, Jeff Guo

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors ...

ROYAL SOC CHEMISTRY2025

Novel Ordering-based Approaches for Causal Structure Learning in the Presence of Unobserved Variables

We propose ordering-based approaches for learning the maximal ancestral graph (MAG) of a structural equation model (SEM) up to its Markov equivalence class (MEC) in the presence of unobserved variables. Existing ordering-based methods in the literature rec ...

Association for the Advancement of Artificial Intelligence (AAAI)2023

The connection of the acyclic disconnection and feedback arc sets - On an open problem of Figueroa et al

Lukas Fritz Felix Vogl

We examine the connection of two graph parameters, the size of a minimum feedback arcs set and the acyclic disconnection. A feedback arc set of a directed graph is a subset of arcs such that after deletion the graph becomes acyclic. The acyclic disconnecti ...

Elsevier2024

Privacy-Preserving Machine Learning on Graphs

Sina Sajadmanesh

Graph Neural Networks (GNNs) have emerged as a powerful tool for learning on graphs, demonstrating exceptional performance in various domains. However, as GNNs become increasingly popular, new challenges arise. One of the most pressing is the need to ensur ...

EPFL2023

Maximum Independent Set: Self-Training through Dynamic Programming

Volkan Cevher, Grigorios Chrysos, Efstratios Panteleimon Skoulakis

This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly construc ...

2023

Graph generative deep learning models with an application to circuit topologies

Igor Krawczuk

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

EPFL2024

The Power of Two Matrices in Spectral Algorithms for Community Recovery

Colin Peter Sandon

Spectral algorithms are some of the main tools in optimization and inference problems on graphs. Typically, the graph is encoded as a matrix and eigenvectors and eigenvalues of the matrix are then used to solve the given graph problem. Spectral algorithms ...

Ieee-Inst Electrical Electronics Engineers Inc2024

GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation

Daniel Gatica-Perez, Sina Sajadmanesh

In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic noise to the GNN's aggregation functio ...

Usenix Assoc2023

Discovering Influencers in Opinion Formation Over Social Graphs

Ali H. Sayed, Mert Kayaalp, Valentina Shumovskaia

The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framework, the agents repeatedly update their beliefs based on private observation ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Towards improving full-length ribosome density prediction by bridging sequence and graph-based representations

Mohan Vamsi Nallapareddy, Pierre Vandergheynst, Felix Naef, Cédric Gobet, Francesco Craighero

Translation elongation plays an important role in regulating protein concentrations in the cell, and dysregulation of this process has been linked to several human diseases. In this study, we use data from ribo-seq experiments to model ribosome densities, ...

PMLR2024

How Deep Neural Networks Learn Compositional Data: The Random Hierarchy Model

Matthieu Wyart, Leonardo Petrini, Alessandro Favero, Francesco Cagnetta, Umberto Maria Tomasini

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional data representatio ...

American Physical Society2024