Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2017
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/1703.05537 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917615108096000 |
|---|---|
| author | Orsini, Francesco Baracchi, Daniele Frasconi, Paolo |
| author_facet | Orsini, Francesco Baracchi, Daniele Frasconi, Paolo |
| contents | We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is able to outperform current state-of-the-art graph classification methods on large social network datasets, while at the same time being competitive on small chemobiological benchmark datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1703_05537 |
| institution | arXiv |
| publishDate | 2017 |
| record_format | arxiv |
| spellingShingle | Shift Aggregate Extract Networks Orsini, Francesco Baracchi, Daniele Frasconi, Paolo Machine Learning We introduce an architecture based on deep hierarchical decompositions to learn effective representations of large graphs. Our framework extends classic R-decompositions used in kernel methods, enabling nested part-of-part relations. Unlike recursive neural networks, which unroll a template on input graphs directly, we unroll a neural network template over the decomposition hierarchy, allowing us to deal with the high degree variability that typically characterize social network graphs. Deep hierarchical decompositions are also amenable to domain compression, a technique that reduces both space and time complexity by exploiting symmetries. We show empirically that our approach is able to outperform current state-of-the-art graph classification methods on large social network datasets, while at the same time being competitive on small chemobiological benchmark datasets. |
| title | Shift Aggregate Extract Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/1703.05537 |