Permutation Invariant Graph Generation via Score-Based Generative
Modeling
- URL: http://arxiv.org/abs/2003.00638v1
- Date: Mon, 2 Mar 2020 03:06:14 GMT
- Title: Permutation Invariant Graph Generation via Score-Based Generative
Modeling
- Authors: Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover,
Stefano Ermon
- Abstract summary: We propose a permutation invariant approach to modeling graphs, using the recent framework of score-based generative modeling.
In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph.
For graph generation, we find that our learning approach achieves better or comparable results to existing models on benchmark datasets.
- Score: 114.12935776726606
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Learning generative models for graph-structured data is challenging because
graphs are discrete, combinatorial, and the underlying data distribution is
invariant to the ordering of nodes. However, most of the existing generative
models for graphs are not invariant to the chosen ordering, which might lead to
an undesirable bias in the learned distribution. To address this difficulty, we
propose a permutation invariant approach to modeling graphs, using the recent
framework of score-based generative modeling. In particular, we design a
permutation equivariant, multi-channel graph neural network to model the
gradient of the data distribution at the input graph (a.k.a., the score
function). This permutation equivariant model of gradients implicitly defines a
permutation invariant distribution for graphs. We train this graph neural
network with score matching and sample from it with annealed Langevin dynamics.
In our experiments, we first demonstrate the capacity of this new architecture
in learning discrete graph algorithms. For graph generation, we find that our
learning approach achieves better or comparable results to existing models on
benchmark datasets.
Related papers
- Discrete Graph Auto-Encoder [52.50288418639075]
We introduce a new framework named Discrete Graph Auto-Encoder (DGAE)
We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations.
In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model.
arXiv Detail & Related papers (2023-06-13T12:40:39Z) - Permutation Equivariant Graph Framelets for Heterophilous Graph Learning [6.679929638714752]
We develop a new way to implement multi-scale extraction via constructing Haar-type graph framelets.
We show that our model can achieve the best performance on certain datasets of heterophilous graphs.
arXiv Detail & Related papers (2023-06-07T09:05:56Z) - AlignGraph: A Group of Generative Models for Graphs [0.0]
It is challenging for generative models to learn a distribution over graphs because of the lack of permutation invariance: nodes may be ordered arbitrarily across graphs, and standard graph alignment is notoriously expensive.
We propose AlignGraph, a group of generative models that combine fast and efficient graph alignment methods with a family of deep generative models that are invariant to node permutations.
Our experiments demonstrate that our framework successfully learns graph distributions, outperforming competitors by 25% -560% in relevant performance scores.
arXiv Detail & Related papers (2023-01-26T18:28:40Z) - GraphGDP: Generative Diffusion Processes for Permutation Invariant Graph
Generation [43.196067037856515]
Graph generative models have broad applications in biology, chemistry and social science.
Current leading autoregressive models fail to capture the permutation invariance nature of graphs.
We propose a continuous-time generative diffusion process for permutation invariant graph generation.
arXiv Detail & Related papers (2022-12-04T15:12:44Z) - 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) - Similarity-aware Positive Instance Sampling for Graph Contrastive
Pre-training [82.68805025636165]
We propose to select positive graph instances directly from existing graphs in the training set.
Our selection is based on certain domain-specific pair-wise similarity measurements.
Besides, we develop an adaptive node-level pre-training method to dynamically mask nodes to distribute them evenly in the graph.
arXiv Detail & Related papers (2022-06-23T20:12:51Z) - 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) - Stochastic Iterative Graph Matching [11.128153575173213]
We propose a new model, Iterative Graph MAtching, to address the graph matching problem.
Our model defines a distribution of matchings for a graph pair so the model can explore a wide range of possible matchings.
We conduct extensive experiments across synthetic graph datasets as well as biochemistry and computer vision applications.
arXiv Detail & Related papers (2021-06-04T02:05:35Z) - A Robust and Generalized Framework for Adversarial Graph Embedding [73.37228022428663]
We propose a robust framework for adversarial graph embedding, named AGE.
AGE generates the fake neighbor nodes as the enhanced negative samples from the implicit distribution.
Based on this framework, we propose three models to handle three types of graph data.
arXiv Detail & Related papers (2021-05-22T07:05:48Z) - Permutation-Invariant Variational Autoencoder for Graph-Level
Representation Learning [0.0]
We propose a permutation-invariant variational autoencoder for graph structured data.
Our model indirectly learns to match the node ordering of input and output graph, without imposing a particular node ordering.
We demonstrate the effectiveness of our proposed model on various graph reconstruction and generation tasks.
arXiv Detail & Related papers (2021-04-20T09:44:41Z)
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.