To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916626217041920 |
|---|---|
| author | Salha-Galvan, Guillaume Xu, Jiaying |
| author_facet | Salha-Galvan, Guillaume Xu, Jiaying |
| contents | This paper investigates the understudied practice of weight sharing (WS) in variational graph autoencoders (VGAE). WS presents both benefits and drawbacks for VGAE model design and node embedding learning, leaving its overall relevance unclear and the question of whether it should be adopted unresolved. We rigorously analyze its implications and, through extensive experiments on a wide range of graphs and VGAE variants, demonstrate that the benefits of WS consistently outweigh its drawbacks. Based on our findings, we recommend WS as an effective approach to optimize, regularize, and simplify VGAE models without significant performance loss. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16724 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders Salha-Galvan, Guillaume Xu, Jiaying Machine Learning Social and Information Networks This paper investigates the understudied practice of weight sharing (WS) in variational graph autoencoders (VGAE). WS presents both benefits and drawbacks for VGAE model design and node embedding learning, leaving its overall relevance unclear and the question of whether it should be adopted unresolved. We rigorously analyze its implications and, through extensive experiments on a wide range of graphs and VGAE variants, demonstrate that the benefits of WS consistently outweigh its drawbacks. Based on our findings, we recommend WS as an effective approach to optimize, regularize, and simplify VGAE models without significant performance loss. |
| title | To Share or Not to Share: Investigating Weight Sharing in Variational Graph Autoencoders |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2502.16724 |