意图漂移下自适应推荐的持续图记忆
Continual Graph Memory for Adaptive Recommendation under Intent Drift
浏览论文内容
中文总结 AI 辅助
针对意图漂移下自适应推荐的问题，本文提出持续图记忆框架CGM-Rec，通过语义图记忆与情景经验记忆互补，在冻结模型参数的情况下仅通过记忆写入实现适配，在多个推荐任务上优于现有基线。
中文摘要 AI 辅助
本文研究意图漂移下的自适应推荐，其中每次推荐结果的反馈可揭示用于排序的关系证据是否有用、缺失或具有误导性。知识图谱（KG）为处理这些变化提供了必要的语义结构，但传统的知识图谱增强系统将图视为静态检索载体，对不断演变的意图、含噪元数据和反复出现的失败模式缺乏适应性。本文提出CGM-Rec，一种用于自适应推荐的持续图记忆框架。CGM-Rec将图状态视为可写记忆，维护两个互补组件：语义图记忆通过质量门控类型操作保守更新，用于存储稳定且高置信度的关系知识；情景经验记忆作为快速反应记忆，学习近期结果、失败案例和修正提示。测试期间，模型参数保持冻结，仅通过记忆写入完成适配。我们在冻结参数的单通重排序协议下评估CGM-Rec，其中编码器和提示在测试期间保持固定，适配仅通过记忆写入实现。在多个推荐设置下的实验表明，CGM-Rec在大多数指标上优于所评估的神经模型和基于大语言模型（LLM）的基线。特别是在采样候选重排序任务中，CGM-Rec在Bundle数据集上较最强的LLM基线将HR@1提升了29.58%；在元数据丰富的ML-100K数据集上，其HR@5为0.5941，优于K-RagRec的0.4746。
英文摘要
This paper studies adaptive recommendation under intent drift, where feedback from each recommendation outcome can reveal whether the relational evidence used for ranking is useful, missing, or misleading. While Knowledge Graphs (KGs) provide essential semantic structure to handle these shifts, traditional KG-enhanced systems treat the graph as a static retrieval substrate, making it brittle to evolving intents, noisy metadata, and recurring failure patterns. This paper proposes CGM-Rec, a continual graph memory framework for adaptive recommendation. CGM-Rec treats the graph state as a writable memory and maintains two complementary components. Therein, a Semantic Graph Memory is updated conservatively through quality-gated typed operations for storing stable and high-confidence relational knowledge. Meanwhile, an Episodic Lesson Memory acts as a fast reactive memory that learns recent outcomes, failure cases, and corrective hints. During testing, model parameters remain frozen and adaptation occurs only through memory writes. We evaluate CGM-Rec under a frozen-parameter, one-pass reranking protocol, where encoders and prompts remain fixed during testing and adaptation occurs only through memory writes. Experiments across multiple recommendation settings show that CGM-Rec improves over evaluated neural and LLM-based baselines on most metrics. Particularly, under sampled-candidate reranking, CGM-Rec improves HR@1 by up to 29.58% over the strongest LLM baseline on Bundle, and outperforms K-RagRec on metadata-rich ML-100K with HR@5 of 0.5941 versus 0.4746.
发表机构
- Phenikaa University（菲卡大学）
- Hanoi University of Science and Technology（河内理工大学）
- University of Technology Sydney（悉尼科技大学）
机构由 AI 辅助整理，请以论文原文为准。
