TD-GEN: Graph Generation With Tree Decomposition
- URL: http://arxiv.org/abs/2106.10656v1
- Date: Sun, 20 Jun 2021 08:57:43 GMT
- Title: TD-GEN: Graph Generation With Tree Decomposition
- Authors: Hamed Shirzad, Hossein Hajimirsadeghi, Amir H. Abdi, Greg Mori
- Abstract summary: TD-GEN is a graph generation framework based on tree decomposition.
Tree nodes are supernodes, each representing a cluster of nodes in the graph.
- Score: 31.751200416677225
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose TD-GEN, a graph generation framework based on tree decomposition,
and introduce a reduced upper bound on the maximum number of decisions needed
for graph generation. The framework includes a permutation invariant tree
generation model which forms the backbone of graph generation. Tree nodes are
supernodes, each representing a cluster of nodes in the graph. Graph nodes and
edges are incrementally generated inside the clusters by traversing the tree
supernodes, respecting the structure of the tree decomposition, and following
node sharing decisions between the clusters. Finally, we discuss the
shortcomings of standard evaluation criteria based on statistical properties of
the generated graphs as performance measures. We propose to compare the
performance of models based on likelihood. Empirical results on a variety of
standard graph generation datasets demonstrate the superior performance of our
method.
Related papers
- HiGen: Hierarchical Graph Generative Networks [2.3931689873603603]
Most real-world graphs exhibit a hierarchical structure, which is often overlooked by existing graph generation methods.
We propose a novel graph generative network that captures the hierarchical nature of graphs and successively generates the graph sub-structures in a coarse-to-fine fashion.
This modular approach enables scalable graph generation for large and complex graphs.
arXiv Detail & Related papers (2023-05-30T18:04:12Z) - 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) - TREE-G: Decision Trees Contesting Graph Neural Networks [33.364191419692105]
TREE-G modifies standard decision trees, by introducing a novel split function that is specialized for graph data.
We show that TREE-G consistently outperforms other tree-based models and often outperforms other graph-learning algorithms such as Graph Neural Networks (GNNs) and Graph Kernels.
arXiv Detail & Related papers (2022-07-06T15:53:17Z) - GTNet: A Tree-Based Deep Graph Learning Architecture [8.50892442127182]
We propose a deep graph learning architecture with a new general message passing scheme that originates from the tree representation of graphs.
Two graph representation learning models are proposed within this GTNet architecture - Graph Tree Attention Network (GTAN) and Graph Tree Convolution Network (GTCN)
arXiv Detail & Related papers (2022-04-27T09:43:14Z) - Reasoning Graph Networks for Kinship Verification: from Star-shaped to
Hierarchical [85.0376670244522]
We investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks.
We develop a Star-shaped Reasoning Graph Network (S-RGN) to exploit more powerful and flexible capacity.
We also develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity.
arXiv Detail & Related papers (2021-09-06T03:16:56Z) - Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised
Node Classification [59.06717774425588]
We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field.
It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations.
We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
arXiv Detail & Related papers (2021-07-27T19:47:53Z) - Order Matters: Probabilistic Modeling of Node Sequence for Graph
Generation [18.03898476141173]
A graph generative model defines a distribution over graphs.
We derive the exact joint probability over the graph and the node ordering of the sequential process.
We train graph generative models by maximizing this bound, without using the ad-hoc node orderings of previous methods.
arXiv Detail & Related papers (2021-06-11T06:37:52Z) - 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) - Graph Neural Networks with Composite Kernels [60.81504431653264]
We re-interpret node aggregation from the perspective of kernel weighting.
We present a framework to consider feature similarity in an aggregation scheme.
We propose feature aggregation as the composition of the original neighbor-based kernel and a learnable kernel to encode feature similarities in a feature space.
arXiv Detail & Related papers (2020-05-16T04:44:29Z) - Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification.
For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes.
Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
arXiv Detail & Related papers (2020-01-17T02:52:30Z)
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.