Towards Robust Representations of Spatial Networks Using Graph Neural Networks
The effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tas...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/15/6918 |
| _version_ | 1797525839824289792 |
|---|---|
| author | Chidubem Iddianozie Gavin McArdle |
| author_facet | Chidubem Iddianozie Gavin McArdle |
| author_sort | Chidubem Iddianozie |
| collection | DOAJ |
| description | The effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tasks on spatial networks. We argue that representations which explicitly encode the relations between spatial entities would improve model performance. Specifically, we consider homogeneous and heterogeneous representations of spatial networks. We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks. Thus, we carry out an empirical study using Graph Neural Network models for two inference tasks on spatial networks. Our results demonstrate that heterogeneous representations improves model performance for down-stream inference tasks on spatial networks. |
| first_indexed | 2024-03-10T09:18:42Z |
| format | Article |
| id | doaj.art-4d244a91ccb0471d9435ca62920fae9f |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T09:18:42Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-4d244a91ccb0471d9435ca62920fae9f2023-11-22T05:21:37ZengMDPI AGApplied Sciences2076-34172021-07-011115691810.3390/app11156918Towards Robust Representations of Spatial Networks Using Graph Neural NetworksChidubem Iddianozie0Gavin McArdle1School of Computer Science, University College Dublin, Dublin 4, IrelandSchool of Computer Science, University College Dublin, Dublin 4, IrelandThe effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tasks on spatial networks. We argue that representations which explicitly encode the relations between spatial entities would improve model performance. Specifically, we consider homogeneous and heterogeneous representations of spatial networks. We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks. Thus, we carry out an empirical study using Graph Neural Network models for two inference tasks on spatial networks. Our results demonstrate that heterogeneous representations improves model performance for down-stream inference tasks on spatial networks.https://www.mdpi.com/2076-3417/11/15/6918spatial networksdata representationsheterogeneous representationsGraph Neural Networks |
| spellingShingle | Chidubem Iddianozie Gavin McArdle Towards Robust Representations of Spatial Networks Using Graph Neural Networks Applied Sciences spatial networks data representations heterogeneous representations Graph Neural Networks |
| title | Towards Robust Representations of Spatial Networks Using Graph Neural Networks |
| title_full | Towards Robust Representations of Spatial Networks Using Graph Neural Networks |
| title_fullStr | Towards Robust Representations of Spatial Networks Using Graph Neural Networks |
| title_full_unstemmed | Towards Robust Representations of Spatial Networks Using Graph Neural Networks |
| title_short | Towards Robust Representations of Spatial Networks Using Graph Neural Networks |
| title_sort | towards robust representations of spatial networks using graph neural networks |
| topic | spatial networks data representations heterogeneous representations Graph Neural Networks |
| url | https://www.mdpi.com/2076-3417/11/15/6918 |
| work_keys_str_mv | AT chidubemiddianozie towardsrobustrepresentationsofspatialnetworksusinggraphneuralnetworks AT gavinmcardle towardsrobustrepresentationsofspatialnetworksusinggraphneuralnetworks |