Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Vignac, Clement"'
Graph diffusion models have emerged as state-of-the-art techniques in graph generation, yet integrating domain knowledge into these models remains challenging. Domain knowledge is particularly important in real-world scenarios, where invalid generate
Externí odkaz:
http://arxiv.org/abs/2406.17341
Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as a cluster
Externí odkaz:
http://arxiv.org/abs/2311.02142
This work introduces MiDi, a novel diffusion model for jointly generating molecular graphs and their corresponding 3D arrangement of atoms. Unlike existing methods that rely on predefined rules to determine molecular bonds based on the 3D conformatio
Externí odkaz:
http://arxiv.org/abs/2302.09048
Autor:
Igashov, Ilia, Stärk, Hannes, Vignac, Clément, Satorras, Victor Garcia, Frossard, Pascal, Welling, Max, Bronstein, Michael, Correia, Bruno
Fragment-based drug discovery has been an effective paradigm in early-stage drug development. An open challenge in this area is designing linkers between disconnected molecular fragments of interest to obtain chemically-relevant candidate drug molecu
Externí odkaz:
http://arxiv.org/abs/2210.05274
Autor:
Vignac, Clement, Krawczuk, Igor, Siraudin, Antoine, Wang, Bohan, Cevher, Volkan, Frossard, Pascal
Publikováno v:
International Conference on Learning Representations (ICLR 2023)
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 add
Externí odkaz:
http://arxiv.org/abs/2209.14734
This work introduces a diffusion model for molecule generation in 3D that is equivariant to Euclidean transformations. Our E(3) Equivariant Diffusion Model (EDM) learns to denoise a diffusion process with an equivariant network that jointly operates
Externí odkaz:
http://arxiv.org/abs/2203.17003
Autor:
Vignac, Clement, Frossard, Pascal
This work addresses one-shot set and graph generation, and, more specifically, the parametrization of probabilistic decoders that map a vector-shaped prior to a distribution over sets or graphs. Sets and graphs are most commonly generated by first sa
Externí odkaz:
http://arxiv.org/abs/2110.02096
Current state of the art algorithms for recommender systems are mainly based on collaborative filtering, which exploits user ratings to discover latent factors in the data. These algorithms unfortunately do not make effective use of other features, w
Externí odkaz:
http://arxiv.org/abs/2010.07050
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 local structures in order to achieve good generalization. However, curre
Externí odkaz:
http://arxiv.org/abs/2006.15107
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the development of graph networks, this setup has become a de facto benchmark for
Externí odkaz:
http://arxiv.org/abs/1911.05384