Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2303.14501 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914645563932672 |
|---|---|
| author | Wittmann, Bastian Paetzold, Johannes C. Prabhakar, Chinmay Rueckert, Daniel Menze, Bjoern |
| author_facet | Wittmann, Bastian Paetzold, Johannes C. Prabhakar, Chinmay Rueckert, Daniel Menze, Bjoern |
| contents | Link prediction algorithms aim to infer the existence of connections (or links) between nodes in network-structured data and are typically applied to refine the connectivity among nodes. In this work, we focus on link prediction for flow-driven spatial networks, which are embedded in a Euclidean space and relate to physical exchange and transportation processes (e.g., blood flow in vessels or traffic flow in road networks). To this end, we propose the Graph Attentive Vectors (GAV) link prediction framework. GAV models simplified dynamics of physical flow in spatial networks via an attentive, neighborhood-aware message-passing paradigm, updating vector embeddings in a constrained manner. We evaluate GAV on eight flow-driven spatial networks given by whole-brain vessel graphs and road networks. GAV demonstrates superior performances across all datasets and metrics and outperformed the state-of-the-art on the ogbl-vessel benchmark at the time of submission by 12% (98.38 vs. 87.98 AUC). All code is publicly available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_14501 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Link Prediction for Flow-Driven Spatial Networks Wittmann, Bastian Paetzold, Johannes C. Prabhakar, Chinmay Rueckert, Daniel Menze, Bjoern Computer Vision and Pattern Recognition Link prediction algorithms aim to infer the existence of connections (or links) between nodes in network-structured data and are typically applied to refine the connectivity among nodes. In this work, we focus on link prediction for flow-driven spatial networks, which are embedded in a Euclidean space and relate to physical exchange and transportation processes (e.g., blood flow in vessels or traffic flow in road networks). To this end, we propose the Graph Attentive Vectors (GAV) link prediction framework. GAV models simplified dynamics of physical flow in spatial networks via an attentive, neighborhood-aware message-passing paradigm, updating vector embeddings in a constrained manner. We evaluate GAV on eight flow-driven spatial networks given by whole-brain vessel graphs and road networks. GAV demonstrates superior performances across all datasets and metrics and outperformed the state-of-the-art on the ogbl-vessel benchmark at the time of submission by 12% (98.38 vs. 87.98 AUC). All code is publicly available on GitHub. |
| title | Link Prediction for Flow-Driven Spatial Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.14501 |