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 available at: https://github.com/seunghan96/AdaTKG

翻译：时序知识图谱（TKG）通过带时间戳的关系事实表示事件，并支持对演化事件进行广泛的推理任务。然而，现有方法生成的实体表示在实体层面是静态的——每个表示仅依赖于学习到的参数，不保留该实体曾参与过的任何交互痕迹。本文突破这种静态视角，提出将每个实体建模为一个自适应过程：每当实体参与事实时，其表示会被动态优化。为此，我们提出AdaTKG模型，该模型为每个实体维护一个随每次观测交互而更新的独立记忆。记忆通过在线方式累积，而预测精度随交互数据的增多持续提升。具体而言，我们将记忆更新实例化为由单一共享标量控制的可学习指数移动平均，而非为每个实体单独使用可学习参数，从而使AdaTKG能处理训练阶段未见的实体。大量实验证明，该方法在TKG基准上取得一致优势，验证了自适应记忆的有效性。代码已开源：https://github.com/seunghan96/AdaTKG