Bridging the Divide: End-to-End Sequence-Graph Learning
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_ | 1866915906518515712 |
|---|---|
| author | Chen, Yuen Wu, Yulun Sharpe, Samuel Melnyk, Igor Nguyen, Nam H. Huang, Furong Bruss, C. Bayan Fathony, Rizal |
| author_facet | Chen, Yuen Wu, Yulun Sharpe, Samuel Melnyk, Igor Nguyen, Nam H. Huang, Furong Bruss, C. Bayan Fathony, Rizal |
| contents | Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its own sequence of events while simultaneously engaging in relationships with others. Existing methods in sequence and graph modeling often overlook one modality in favor of the other. We argue that these two facets should instead be integrated and learned jointly. We introduce BRIDGE, a unified end-to-end architecture that couples a sequence model with a graph module under a single objective, allowing gradients to flow across both components to learn task-aligned representations. To enable fine-grained interaction, we propose TOKENXATTN, a token-level cross-attention layer that facilitates message passing between specific events in neighboring sequences. Across two settings, relationship prediction and fraud detection, BRIDGE consistently outperforms static graph models, temporal graph methods, as well as sequence-only baselines on both ranking and classification metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25126 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging the Divide: End-to-End Sequence-Graph Learning Chen, Yuen Wu, Yulun Sharpe, Samuel Melnyk, Igor Nguyen, Nam H. Huang, Furong Bruss, C. Bayan Fathony, Rizal Machine Learning Artificial Intelligence Many real-world prediction tasks, particularly those involving entities such as customers or patients, involve both {sequential} and {relational} data. Each entity maintains its own sequence of events while simultaneously engaging in relationships with others. Existing methods in sequence and graph modeling often overlook one modality in favor of the other. We argue that these two facets should instead be integrated and learned jointly. We introduce BRIDGE, a unified end-to-end architecture that couples a sequence model with a graph module under a single objective, allowing gradients to flow across both components to learn task-aligned representations. To enable fine-grained interaction, we propose TOKENXATTN, a token-level cross-attention layer that facilitates message passing between specific events in neighboring sequences. Across two settings, relationship prediction and fraud detection, BRIDGE consistently outperforms static graph models, temporal graph methods, as well as sequence-only baselines on both ranking and classification metrics. |
| title | Bridging the Divide: End-to-End Sequence-Graph Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.25126 |