提出知识图谱记忆中短时到长时信息的智能迁移方法
Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability
- 设计基于符号与神经网络结合的决策机制，判断是否保留观察到的知识三元组
- 在128容量下优于符号与神经基线，尤其能保留导航和查询相关事实
- 模型可解释性强，适合需要可解释记忆决策的应用场景
部分可观测环境下的强化学习需决定保留哪些信息，但现有基于记忆的方法未显式建模符号观测从短时到长时的转移。本文研究时间知识图谱记忆中的这一过程，将其建模为神经符号值函数决策问题：对每个观测三元组，代理选择是否在长期插入前保留或丢弃。为处理可变大小的短时缓冲区，采用共享参数的逐项Q-learning设计，并在连续步骤中匹配项上进行实用的时间差更新。在长时记忆容量为128的RoomKG基准上，所学转移策略优于符号与神经基线，包括带时间标注的符号基线及基于历史的LSTM/Transformer基线。不同转移策略消融实验表明，轻量级仅依赖短时局部信息的变体表现最佳；步骤级行为分析显示，该策略保留导航与查询相关事实，舍弃低价值候选事实，验证了在内存约束下可显式、可解释的记忆决策。
原文摘要 · Abstract (English)
Reinforcement learning under partial observability requires deciding what information to retain, yet most memory-based approaches do not explicitly model short-term-to-long-term transfer of symbolic observations. We study this transfer process in a temporal knowledge-graph memory setting and cast it as a neuro-symbolic value-based decision problem: for each observed triple, the agent chooses whether to keep or drop it before long-term insertion. To handle variable-sized short-term buffers, we use a per-item Q-learning design with shared parameters and a practical temporal-difference update over matched items across consecutive steps. On the RoomKG benchmark at long-term memory capacity 128, learned transfer decisions outperform symbolic and neural baselines, including symbolic baselines with temporal annotations and history-based LSTM/Transformer baselines. Across transfer-policy ablations, a lightweight local short-term-only variant performs best, and step-level behavior shows that the policy keeps navigation- and query-relevant facts while discarding lower-value candidate facts, supporting explicit and interpretable memory decisions under memory constraints.
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。