Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911726721564672 |
|---|---|
| author | Chang, Qian Giurcaneanu, Ciprian Doru Jia, Runsong Li, Xia Hu, Guoping Cheng, Xiufeng Yang, Jinqing Wu, Mengjia Zhang, Yi |
| author_facet | Chang, Qian Giurcaneanu, Ciprian Doru Jia, Runsong Li, Xia Hu, Guoping Cheng, Xiufeng Yang, Jinqing Wu, Mengjia Zhang, Yi |
| contents | Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths, limiting their ability to generalize across graphs with diverse interaction frequencies and topological characteristics. We propose Dual-Scale Retentive Dynamics (DSRD), a unified framework that maintains a retentive representation state encoding both temporal memory and structural context. DSRD introduces two key components: (i) a retentive state with dual-scale adaptation that jointly models temporal dynamics and structural propagation within a single recurrent formulation, and (ii) adaptive decay kernels with learnable time-sensitivity parameters that automatically balance short-term responsiveness and long-term retention based on the underlying interaction patterns. We provide theoretical analysis establishing the equivalence between event-wise parallel aggregation and efficient recurrent state updates, as well as stability and boundedness guarantees for the learned dynamics. Extensive experiments on 14 real-world benchmarks demonstrate that DSRD consistently achieves state-of-the-art performance on both link prediction and node classification tasks, with strong generalization across transductive and inductive settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_29453 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs Chang, Qian Giurcaneanu, Ciprian Doru Jia, Runsong Li, Xia Hu, Guoping Cheng, Xiufeng Yang, Jinqing Wu, Mengjia Zhang, Yi Machine Learning Artificial Intelligence Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typically adopt fixed temporal decay schemes or predetermined structural propagation depths, limiting their ability to generalize across graphs with diverse interaction frequencies and topological characteristics. We propose Dual-Scale Retentive Dynamics (DSRD), a unified framework that maintains a retentive representation state encoding both temporal memory and structural context. DSRD introduces two key components: (i) a retentive state with dual-scale adaptation that jointly models temporal dynamics and structural propagation within a single recurrent formulation, and (ii) adaptive decay kernels with learnable time-sensitivity parameters that automatically balance short-term responsiveness and long-term retention based on the underlying interaction patterns. We provide theoretical analysis establishing the equivalence between event-wise parallel aggregation and efficient recurrent state updates, as well as stability and boundedness guarantees for the learned dynamics. Extensive experiments on 14 real-world benchmarks demonstrate that DSRD consistently achieves state-of-the-art performance on both link prediction and node classification tasks, with strong generalization across transductive and inductive settings. |
| title | Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2605.29453 |