Publication
Equivariant Neural Architectures for Representing and Generating Graphs
Publications associées (316)
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 ...
2023GAP: 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 ...
Berkeley2023Novel 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)2023Privacy-Preserving Machine Learning on Graphs
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 ...
EPFL2023DiGress: Discrete Denoising diffusion for graph generation
Pascal Frossard, Volkan Cevher, Igor Krawczuk, Bohan Wang, Clément Arthur Yvon Vignac
This work introduces DiGress, a discrete denoising diffusion model for generating graphs with categorical node and edge attributes. Our model utilizes a discrete diffusion process that progressively edits graphs with noise, through the process of adding or ...
2023Acceleration of graph pattern mining and applications to financial crime
Various forms of real-world data, such as social, financial, and biological networks, can berepresented using graphs. An efficient method of analysing this type of data is to extractsubgraph patterns, such as cliques, cycles, and motifs, from graphs. For i ...
EPFL2023Graph neural networks for dynamic modeling of roller bearings
Machine learning has paved the way for the real-time monitoring of complex infrastructure and industrial systems. However, purely data-driven methods have not been able to learn the underlying dynamics and generalize them to operating conditions that have ...
PHM Society2023Unsupervised Graph Representation Learning with Cluster-aware Self-training and Refining
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous Graph Neural Networks (GNN) require a large number of labeled ...
New York2023Beyond Spectral Gap: The Role of the Topology in Decentralized Learning
Martin Jaggi, Thijs Vogels, Hadrien Hendrikx
In data-parallel optimization of machine learning models, workers collaborate to improve their estimates of the model: more accurate gradients allow them to use larger learning rates and optimize faster. In the decentralized setting, in which workers commu ...
Brookline2023Backpropagation-free training of deep physical neural networks
Romain Christophe Rémy Fleury, Ali Momeni, Matthieu Francis Malléjac, Babak Rahmani, Marc Philipp Del Hougne
Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption and scalability issues. Current training of digital deep-learning models primarily relies on backpropagation that ...
2023