CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
- URL: http://arxiv.org/abs/2110.03800v1
- Date: Thu, 7 Oct 2021 21:24:07 GMT
- Title: CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation
- Authors: Matin Yousefabadi, Yassaman Ommi, Faezeh Faez, Amirmojtaba Sabour,
Mahdieh Soleymani Baghshah, Hamid R. Rabiee
- Abstract summary: We introduce the Class Conditioned Graph Generator (CCGG) to generate graphs with desired features.
CCGG outperforms existing conditional graph generation methods on various datasets.
It also manages to maintain the quality of the generated graphs in terms of distribution-based evaluation metrics.
- Score: 7.37333913697359
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph data structures are fundamental for studying connected entities. With
an increase in the number of applications where data is represented as graphs,
the problem of graph generation has recently become a hot topic in many signal
processing areas. However, despite its significance, conditional graph
generation that creates graphs with desired features is relatively less
explored in previous studies. This paper addresses the problem of
class-conditional graph generation that uses class labels as generation
constraints by introducing the Class Conditioned Graph Generator (CCGG). We
built CCGG by adding the class information as an additional input to a graph
generator model and including a classification loss in its total loss along
with a gradient passing trick. Our experiments show that CCGG outperforms
existing conditional graph generation methods on various datasets. It also
manages to maintain the quality of the generated graphs in terms of
distribution-based evaluation metrics.
Related papers
Err
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.