Generating a Doppelganger Graph: Resembling but Distinct Article Swipe

MAKE IMPACT

Yuliang Ji , Ru Huang , Jie Chen , Yuanzhe Xi · YOU? · · 2021 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2101.09593

Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e.g., images and sound waves). With the emergence of deep models for graph structured data, natural interests seek extensions of these generative models for graphs. Successful extensions were seen recently in the case of learning from a collection of graphs (e.g., protein data banks), but the learning from a single graph has been largely under explored. The latter case, however, is important in practice. For example, graphs in financial and healthcare systems contain so much confidential information that their public accessibility is nearly impossible, but open science in these fields can only advance when similar data are available for benchmarking. In this work, we propose an approach to generating a doppelganger graph that resembles a given one in many graph properties but nonetheless can hardly be used to reverse engineer the original one, in the sense of a near zero edge overlap. The approach is an orchestration of graph representation learning, generative adversarial networks, and graph realization algorithms. Through comparison with several graph generative models (either parameterized by neural networks or not), we demonstrate that our result barely reproduces the given graph but closely matches its properties. We further show that downstream tasks, such as node classification, on the generated graphs reach similar performance to the use of the original ones.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2101.09593

PDF

https://arxiv.org/pdf/2101.09593

OA Status

green

Cited By

1

References

43

Related Works

10

OpenAlex ID

https://openalex.org/W3121397452

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3121397452

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2101.09593

Digital Object Identifier

Title

Generating a Doppelganger Graph: Resembling but Distinct

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2021

Year of publication

Publication date

2021-01-23

Full publication date if available

Authors

Yuliang Ji, Ru Huang, Jie Chen, Yuanzhe Xi

List of authors in order

Landing page

https://arxiv.org/abs/2101.09593

Publisher landing page

PDF URL

https://arxiv.org/pdf/2101.09593

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2101.09593

Direct OA link when available

Concepts

Computer science, Generative grammar, Theoretical computer science, Parameterized complexity, Null model, Graph, Generative model, Artificial intelligence, Algorithm, Mathematics, Combinatorics

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2022: 1

Per-year citation counts (last 5 years)

References (count)

43

Number of works referenced by this work

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload