Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.11836 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912706159706112 |
|---|---|
| author | Gao, Jian Wu, Jianshe Ding, JingYi |
| author_facet | Gao, Jian Wu, Jianshe Ding, JingYi |
| contents | Learning representations for continuous-time dynamic graphs is critical for dynamic link prediction. While recent methods have become increasingly complex, the field lacks a strong and informative baseline to reliably gauge progress. This paper proposes HyperEvent, a simple approach that captures relative structural patterns in event sequences through an intuitive encoding mechanism. As a straightforward baseline, HyperEvent leverages relative structural encoding to identify meaningful event sequences without complex parameterization. By combining these interpretable features with a lightweight transformer classifier, HyperEvent reframes link prediction as event structure recognition. Despite its simplicity, HyperEvent achieves competitive results across multiple benchmarks, often matching the performance of more complex models. This work demonstrates that effective modeling can be achieved through simple structural encoding, providing a clear reference point for evaluating future advancements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_11836 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encoding Gao, Jian Wu, Jianshe Ding, JingYi Machine Learning Learning representations for continuous-time dynamic graphs is critical for dynamic link prediction. While recent methods have become increasingly complex, the field lacks a strong and informative baseline to reliably gauge progress. This paper proposes HyperEvent, a simple approach that captures relative structural patterns in event sequences through an intuitive encoding mechanism. As a straightforward baseline, HyperEvent leverages relative structural encoding to identify meaningful event sequences without complex parameterization. By combining these interpretable features with a lightweight transformer classifier, HyperEvent reframes link prediction as event structure recognition. Despite its simplicity, HyperEvent achieves competitive results across multiple benchmarks, often matching the performance of more complex models. This work demonstrates that effective modeling can be achieved through simple structural encoding, providing a clear reference point for evaluating future advancements. |
| title | HyperEvent: A Strong Baseline for Dynamic Link Prediction via Relative Structural Encoding |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.11836 |