AI 中文总结
研究持续时间知识图谱推理中表征冲突问题，提出MA-DAR框架，通过流形对齐减轻分布差异，用动态门控机制确定融合权重，经极化正则化器鼓励果断路由行为，实验证明该框架有效提升TKG编码器性能。
AI 中文摘要
持续时间知识图谱（TKG）推理旨在持续纳入新出现的事实，同时保留先前获取的知识。基于回放的持续学习通过重温历史表征取得了有前景的性能。然而，现有方法主要关注回放内容，而很大程度上忽略了回放表征应如何与当前表征整合。这种直接整合常引发两种关键的表征冲突形式：“范数主导”和“语义模糊”，最终降低持续推理性能。为应对这些挑战，我们提出MA-DAR（流形对齐动态自适应路由），一种用于回放表征融合的轻量级即插即用框架。MA-DAR首先将回放和当前表征对齐到共享流形上以减轻分布差异。然后采用动态门控机制学习维度融合权重，自适应确定回放和当前表征对融合表征的贡献。此外，极化正则化器通过抑制模糊门控决策鼓励更果断的路由行为，实现更稳定有效的知识整合。在四个公共持续TKG基准上的大量实验表明，MA-DAR持续提升代表性TKG编码器的性能，且在不同回放设置下均有效。综合消融研究和可视化分析进一步验证了流形对齐和动态自适应路由在减轻表征冲突及改善持续推理方面的有效性。
英文摘要
Continual temporal knowledge graph (TKG) reasoning aims to continuously incorporate newly emerging facts while preserving previously acquired knowledge. Replay-based continual learning has achieved promising performance by revisiting historical representations. However, existing methods primarily focus on what to replay, while largely overlooking how replayed representations should be integrated with current ones. Such direct integration often gives rise to two critical forms of representation conflict: \textit{norm domination} and \textit{semantic blurring}, ultimately degrading continual reasoning performance. To address these challenges, we propose MA-DAR (Manifold-Aligned Dynamic Adaptive Routing), a lightweight plug-and-play framework for replay representation fusion. MA-DAR first aligns replayed and current representations onto a shared manifold to alleviate distribution discrepancies. It then employs a dynamic gating mechanism to learn dimension-wise fusion weights, adaptively determining the contribution of replayed and current representations to the fused representation. Furthermore, a polarization regularizer encourages more decisive routing behaviors by discouraging ambiguous gating decisions, resulting in more stable and effective knowledge integration. Extensive experiments on four public continual TKG benchmarks demonstrate that MA-DAR consistently improves the performance of representative TKG encoders while remaining effective under different replay settings. Comprehensive ablation studies and visualization analyses further verify the effectiveness of manifold alignment and dynamic adaptive routing in mitigating representation conflicts and improving continual reasoning.
