Graph synthesis is a long-standing research problem. Many deep neural networks that learn about latent characteristics of graphs and generate fake graphs have been proposed. However, in many cases their scalability is too high to be used to synthesize large graphs. Recently, one work proposed an interesting scalable idea to learn and generate random walks that can be merged into a graph. Due to its difficulty, however, the random walk-based graph synthesis failed to show state-of-the-art performance in many cases. We present an improved random walk-based method by using negative random walks. In our experiments with 6 datasets and 8 baseline methods, our method shows the best performance in almost all cases. We achieve both high scalability and generation quality.
|Title of host publication||SIAM International Conference on Data Mining, SDM 2021|
|Number of pages||9|
|Publication status||Published - 2021|
|Event||2021 SIAM International Conference on Data Mining, SDM 2021 - Virtual, Online|
Duration: 2021 Apr 29 → 2021 May 1
|Name||SIAM International Conference on Data Mining, SDM 2021|
|Conference||2021 SIAM International Conference on Data Mining, SDM 2021|
|Period||21/4/29 → 21/5/1|
Bibliographical noteFunding Information:
Noseong Park (firstname.lastname@example.org) is the corresponding author. This work was partially supported by the IITP of the Korea government (MSIT) under grant 2020-0-01361, Artificial Intelligence Graduate School Program (Yonsei University), by the Office of Naval Research under grants N00014-18-1-2670 and N00014-20-1-2407, by the Army Research Office under grant W911NF-13-1-0421, and by the National Science Foundation under grant CNS-1822094.
© 2021 by SIAM.
All Science Journal Classification (ASJC) codes
- Computer Science Applications