为时序知识图谱设计可自适应更新的实体记忆机制，提升动态事件推理效果。
AdaTKG: Adaptive Memory for Temporal Knowledge Graph Reasoning
- 每个实体维护一个在线更新的记忆，随参与事件动态优化表示。
- 在多个基准数据集上超越现有方法，尤其在未见实体上表现更优。
- 采用共享标量控制记忆更新，支持训练外实体的推理，适合动态场景。
时序知识图谱（TKG）表示带时间戳的关系事实，支持对演化事件的多种推理任务。然而，现有方法生成的实体表示在实体层面是静态的，仅依赖学习参数，不保留实体参与交互的历史痕迹。本文提出突破这一静态视角，将每个实体建模为自适应过程，其表示在每次参与事实时均被更新。为此，我们提出AdaTKG，为每个实体维护一个随观测交互不断更新的记忆，记忆在线累积，预测性能随更多交互到达而持续提升。具体地，我们将记忆更新设计为由单个共享标量控制的可学习指数移动平均，而非为每个实体使用可学习参数，从而实现对训练中未见实体的支持。大量实验表明，该方法在多个基准上持续优于现有TKG基线，验证了自适应记忆的有效性。代码已公开于：https://github.com/seunghan96/AdaTKG
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。