AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914542937702400 |
|---|---|
| author | Lee, Seunghan Seo, Jun Lee, Jaehoon Yoo, Sungdong Kim, Minjae Lim, Tae Yoon Kang, Dongwan Choi, Hwanil Lee, SoonYoung Ahn, Wonbin |
| author_facet | Lee, Seunghan Seo, Jun Lee, Jaehoon Yoo, Sungdong Kim, Minjae Lim, Tae Yoon Kang, Dongwan Choi, Hwanil Lee, SoonYoung Ahn, Wonbin |
| contents | Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters only and retains no trace of the interactions in which the entity has participated. In this paper, we depart from this static view and propose that each entity be modeled as an adaptive process whose representation is refined every time the entity participates in a fact. To this end, we propose AdaTKG, which maintains a per-entity memory that is updated with every observed interaction, with the memory accumulating online and predictions improving as more interactions arrive. Specifically, we instantiate the memory update as a learnable exponential moving average governed by a single shared scalar instead of using learnable parameters for each entity, enabling AdaTKG to handle entities unseen during training. Extensive experiments confirm consistent gains over TKG baselines, demonstrating the effectiveness of adaptive memory. Code is publicly available at: https://github.com/seunghan96/AdaTKG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07121 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning Lee, Seunghan Seo, Jun Lee, Jaehoon Yoo, Sungdong Kim, Minjae Lim, Tae Yoon Kang, Dongwan Choi, Hwanil Lee, SoonYoung Ahn, Wonbin Artificial Intelligence Machine Learning Temporal knowledge graphs (TKGs) represent time-stamped relational facts and support a wide range of reasoning tasks over evolving events. However, existing methods produce entity representations that are static at the entity level, in that each representation is a function of learned parameters only and retains no trace of the interactions in which the entity has participated. In this paper, we depart from this static view and propose that each entity be modeled as an adaptive process whose representation is refined every time the entity participates in a fact. To this end, we propose AdaTKG, which maintains a per-entity memory that is updated with every observed interaction, with the memory accumulating online and predictions improving as more interactions arrive. Specifically, we instantiate the memory update as a learnable exponential moving average governed by a single shared scalar instead of using learnable parameters for each entity, enabling AdaTKG to handle entities unseen during training. Extensive experiments confirm consistent gains over TKG baselines, demonstrating the effectiveness of adaptive memory. Code is publicly available at: https://github.com/seunghan96/AdaTKG. |
| title | AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2605.07121 |