DiGress: Discrete Denoising diffusion for graph generation
- URL: http://arxiv.org/abs/2209.14734v4
- Date: Tue, 23 May 2023 10:32:08 GMT
- Title: DiGress: Discrete Denoising diffusion for graph generation
- Authors: Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan
Cevher, Pascal Frossard
- Abstract summary: DiGress is a discrete denoising diffusion model for generating graphs with categorical node and edge attributes.
It achieves state-of-the-art performance on molecular and non-molecular datasets, with up to 3x validity improvement.
It is also the first model to scale to the large GuacaMol dataset containing 1.3M drug-like molecules.
- Score: 79.13904438217592
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: 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 removing edges and changing the categories. A
graph transformer network is trained to revert this process, simplifying the
problem of distribution learning over graphs into a sequence of node and edge
classification tasks. We further improve sample quality by introducing a
Markovian noise model that preserves the marginal distribution of node and edge
types during diffusion, and by incorporating auxiliary graph-theoretic
features. A procedure for conditioning the generation on graph-level features
is also proposed. DiGress achieves state-of-the-art performance on molecular
and non-molecular datasets, with up to 3x validity improvement on a planar
graph dataset. It is also the first model to scale to the large GuacaMol
dataset containing 1.3M drug-like molecules without the use of
molecule-specific representations.
Related papers
- IFH: a Diffusion Framework for Flexible Design of Graph Generative Models [53.219279193440734]
Graph generative models can be classified into two prominent families: one-shot models, which generate a graph in one go, and sequential models, which generate a graph by successive additions of nodes and edges.
This paper proposes a graph generative model, called Insert-Fill-Halt (IFH), that supports the specification of a sequentiality degree.
arXiv Detail & Related papers (2024-08-23T16:24:40Z) - Learning to Approximate Adaptive Kernel Convolution on Graphs [4.434835769977399]
We propose a diffusion learning framework, where the range of feature aggregation is controlled by the scale of a diffusion kernel.
Our model is tested on various standard for node-wise classification for the state-of-the-art datasets performance.
It is also validated on a real-world brain network data for graph classifications to demonstrate its practicality for Alzheimer classification.
arXiv Detail & Related papers (2024-01-22T10:57:11Z) - Leveraging Graph Diffusion Models for Network Refinement Tasks [72.54590628084178]
We propose a novel graph generative framework, SGDM, based on subgraph diffusion.
Our framework not only improves the scalability and fidelity of graph diffusion models, but also leverages the reverse process to perform novel, conditional generation tasks.
arXiv Detail & Related papers (2023-11-29T18:02:29Z) - Autoregressive Diffusion Model for Graph Generation [12.390149720274904]
We propose an emphautoregressive diffusion model for graph generation.
Unlike existing methods, we define a node-absorbing diffusion process that operates directly in the discrete graph space.
Our experiments on six diverse generic graph datasets and two molecule datasets show that our model achieves better or comparable generation performance with previous state-of-the-art.
arXiv Detail & Related papers (2023-07-17T21:21:18Z) - Addressing Heterophily in Node Classification with Graph Echo State
Networks [11.52174067809364]
We address the challenges of heterophilic graphs with Graph Echo State Network (GESN) for node classification.
GESN is a reservoir computing model for graphs, where node embeddings are computed by an untrained message-passing function.
Our experiments show that reservoir models are able to achieve better or comparable accuracy with respect to most fully trained deep models.
arXiv Detail & Related papers (2023-05-14T19:42:31Z) - Graph Generation with Diffusion Mixture [57.78958552860948]
Generation of graphs is a major challenge for real-world tasks that require understanding the complex nature of their non-Euclidean structures.
We propose a generative framework that models the topology of graphs by explicitly learning the final graph structures of the diffusion process.
arXiv Detail & Related papers (2023-02-07T17:07:46Z) - Conditional Diffusion Based on Discrete Graph Structures for Molecular
Graph Generation [32.66694406638287]
We propose a Conditional Diffusion model based on discrete Graph Structures (CDGS) for molecular graph generation.
Specifically, we construct a forward graph diffusion process on both graph structures and inherent features through differential equations (SDE)
We present a specialized hybrid graph noise prediction model that extracts the global context and the local node-edge dependency from intermediate graph states.
arXiv Detail & Related papers (2023-01-01T15:24:15Z) - GrannGAN: Graph annotation generative adversarial networks [72.66289932625742]
We consider the problem of modelling high-dimensional distributions and generating new examples of data with complex relational feature structure coherent with a graph skeleton.
The model we propose tackles the problem of generating the data features constrained by the specific graph structure of each data point by splitting the task into two phases.
In the first it models the distribution of features associated with the nodes of the given graph, in the second it complements the edge features conditionally on the node features.
arXiv Detail & Related papers (2022-12-01T11:49:07Z) - Node Copying: A Random Graph Model for Effective Graph Sampling [35.957719744856696]
We introduce the node copying model for constructing a distribution over graphs.
We show the usefulness of the copying model in three tasks.
We employ our proposed model to mitigate the effect of adversarial attacks on the graph topology.
arXiv Detail & Related papers (2022-08-04T04:04:49Z) - Score-based Generative Modeling of Graphs via the System of Stochastic
Differential Equations [57.15855198512551]
We propose a novel score-based generative model for graphs with a continuous-time framework.
We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
arXiv Detail & Related papers (2022-02-05T08:21:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.