Temporal Knowledge Graph (TKG) is an extension of traditional Knowledge Graph (KG) that incorporates the dimension of time. Reasoning on TKGs is a crucial task that aims to predict future facts based on historical occurrences. The key challenge lies in uncovering structural dependencies within historical subgraphs and temporal patterns. Most existing approaches model TKGs relying on entity modeling, as nodes in the graph play a crucial role in knowledge representation. However, the real-world scenario often involves an extensive number of entities, with new entities emerging over time. This makes it challenging for entity-dependent methods to cope with extensive volumes of entities, and effectively handling newly emerging entities also becomes a significant challenge. Therefore, we propose Temporal Inductive Path Neural Network (TiPNN), which models historical information in an entity-independent perspective. Specifically, TiPNN adopts a unified graph, namely history temporal graph, to comprehensively capture and encapsulate information from history. Subsequently, we utilize the defined query-aware temporal paths on a history temporal graph to model historical path information related to queries for reasoning. Extensive experiments illustrate that the proposed model not only attains significant performance enhancements but also handles inductive settings, while additionally facilitating the provision of reasoning evidence through history temporal graphs.

翻译：时序知识图谱（Temporal Knowledge Graph, TKG）是传统知识图谱（Knowledge Graph, KG）在时间维度上的扩展。基于TKG的推理旨在根据历史事件预测未来事实，其核心挑战在于挖掘历史子图的结构依赖关系与时间模式。现有方法多依赖实体建模（因图中的节点在知识表示中起关键作用），但现实场景中通常包含大量实体，且新实体随时间不断涌现，这使得依赖实体的方法难以处理海量实体，同时有效应对新增实体也面临重大挑战。为此，我们提出时序归纳路径神经网络（Temporal Inductive Path Neural Network, TiPNN），以实体无关的视角建模历史信息。具体而言，TiPNN采用统一的历史时序图（history temporal graph）全面捕获并封装历史信息，随后利用定义在该图上的查询感知时序路径（query-aware temporal paths），建模与查询相关的历史路径信息进行推理。大量实验表明，所提模型不仅显著提升了推理性能，还能处理归纳设置，同时可通过历史时序图提供推理证据辅助解释。