On the Role of Edge Dependency in Graph Generative Models

Sudhanshu Chanpuriya, Cameron N Musco, Konstantinos Sotiropoulos, Charalampos Tsourakakis

Primary Area: learning on graphs and other geometries & topologies

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: graph, network, generative, model, random, dependence, overlap, triangle, cycle, bound

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We introduce a novel hierarchical categorization of graph generative models based on their edge and node dependencies.

Abstract: In this work, we introduce a novel evaluation framework for generative models of graphs, emphasizing the importance of model-generated graph *overlap* (Chanpuriya et al., 2021) to ensure both accuracy and edge-diversity. We delineate a hierarchy of graph generative models categorized into three levels of complexity: edge independent, node independent, and fully dependent models. This hierarchy encapsulates a wide range of prevalent methods. We derive theoretical bounds on the number of triangles and other short-length cycles producible by each level of the hierarchy, contingent on the model overlap. We provide instances demonstrating the asymptotic optimality of our bounds. Furthermore, we introduce new generative models for each of the three hierarchical levels, leveraging dense subgraph discovery (Gionis & Tsourakakis, 2015). Our evaluation, conducted on real-world datasets, focuses on assessing the output quality and overlap of our proposed models in comparison to other popular models. Our results indicate that our simple, interpretable models provide competitive baselines to popular generative models. Through this investigation, we aim to propel the advancement of graph generative models by offering a structured framework and robust evaluation metrics, thereby facilitating the development of models capable of generating accurate and edge-diverse graphs.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 8471