Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2305.19125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917621917548544 |
|---|---|
| author | Jang, Yunhui Kim, Dongwoo Ahn, Sungsoo |
| author_facet | Jang, Yunhui Kim, Dongwoo Ahn, Sungsoo |
| contents | Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis. In this work, we introduce a novel graph generation method leveraging $K^2$-tree representation, originally designed for lossless graph compression. The $K^2$-tree representation {encompasses inherent hierarchy while enabling compact graph generation}. In addition, we make contributions by (1) presenting a sequential $K^2$-treerepresentation that incorporates pruning, flattening, and tokenization processes and (2) introducing a Transformer-based architecture designed to generate the sequence by incorporating a specialized tree positional encoding scheme. Finally, we extensively evaluate our algorithm on four general and two molecular graph datasets to confirm its superiority for graph generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_19125 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Graph Generation with $K^2$-trees Jang, Yunhui Kim, Dongwoo Ahn, Sungsoo Machine Learning Artificial Intelligence Social and Information Networks Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis. In this work, we introduce a novel graph generation method leveraging $K^2$-tree representation, originally designed for lossless graph compression. The $K^2$-tree representation {encompasses inherent hierarchy while enabling compact graph generation}. In addition, we make contributions by (1) presenting a sequential $K^2$-treerepresentation that incorporates pruning, flattening, and tokenization processes and (2) introducing a Transformer-based architecture designed to generate the sequence by incorporating a specialized tree positional encoding scheme. Finally, we extensively evaluate our algorithm on four general and two molecular graph datasets to confirm its superiority for graph generation. |
| title | Graph Generation with $K^2$-trees |
| topic | Machine Learning Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2305.19125 |