📄 中文摘要
时间知识图谱（TKG）预测需要通过联合建模每个快照内的结构依赖关系和跨快照的时间演变来预测未来事实。然而，大多数现有方法是无状态的：它们在每个时间戳重新计算实体表示，依赖有限的查询窗口，导致情节遗忘和长期依赖的快速衰减。为了解决这一限制，提出了一种名为实体状态调优（EST）的框架，该框架与编码器无关，为TKG预测器提供持久且持续演变的实体状态。EST维护一个全局状态缓冲区，并通过闭环设计逐步对齐结构证据与序列信号。具体而言，拓扑感知状态感知器首先对...
超越快照的演变：通过实体状态调优实现结构与序列的协调，以进行时间知识图谱预测
📄 English Summary
Evolving Beyond Snapshots: Harmonizing Structure and Sequence via Entity State Tuning for Temporal Knowledge Graph Forecasting
Temporal knowledge graph (TKG) forecasting necessitates predicting future facts by jointly modeling structural dependencies within each snapshot and temporal evolution across snapshots. However, most existing methods are stateless, recomputing entity representations at each timestamp from a limited query window, resulting in episodic amnesia and rapid decay of long-term dependencies. To address this limitation, Entity State Tuning (EST) is proposed as an encoder-agnostic framework that equips TKG forecasters with persistent and continuously evolving entity states. EST maintains a global state buffer and progressively aligns structural evidence with sequential signals through a closed-loop design. Specifically, a topology-aware state perceiver first injects...