arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.07580cs.IRcs.AI
收藏

DynLLM:当大语言模型遇上动态图推荐

DynLLM: When Large Language Models Meet Dynamic Graph Recommendation

University of Science and Technology of China(中国科学技术大学);Alibaba Group(阿里巴巴集团)

Ziwei Zhao, Fake Lin, Xi Zhu, Zhi Zheng, Tong Xu, Shitian Shen, Xueying Li, Zikai Yin, Enhong Chen

AI总结:

针对现有图增强方法难以应对动态图推荐的问题,提出DynLLM框架,利用LLM生成多维度用户画像并通过蒸馏注意力机制优化嵌入,与连续时间动态图嵌入融合,在电商数据集上取得优于基线的效果。

摘要:

过去一年,大语言模型(LLMs)在推荐系统中的潜在应用引发了广泛关注,其有望缓解长期存在的数据稀疏性问题。尽管已有大量研究致力于用户-物品图增强以提升基于图的推荐性能,但这些方法可能难以应对动态图推荐任务——该任务同时涉及结构和时间层面的图动态性,处理时序演化数据存在固有复杂性。为填补这一空白,本文提出了一种名为DynLLM的新型框架,借助LLMs处理动态图推荐任务。具体而言,DynLLM利用LLMs的能力,基于历史购买记录的丰富文本特征生成多维度用户画像,包括人群细分、个人兴趣、偏好品类和喜爱品牌,进而补充并丰富用户与物品之间的潜在关系。在此思路下,为将多维度画像与时序图嵌入相融合,我们利用LLMs生成对应的画像嵌入,并进一步采用蒸馏注意力机制优化LLM生成的画像嵌入以缓解噪声信号,同时评估并调整每个蒸馏后的维度嵌入的相关性,以实现与连续时间动态图(CTDGs)时序图嵌入的无缝融合。在两个真实电商数据集上的大量实验验证了,DynLLM相较于多种主流基线方法具有更优的性能提升。

英文摘要:

Last year has witnessed the considerable interest of Large Language Models (LLMs) for their potential applications in recommender systems, which may mitigate the persistent issue of data sparsity. Though large efforts have been made for user-item graph augmentation with better graph-based recommendation performance, they may fail to deal with the dynamic graph recommendation task, which involves both structural and temporal graph dynamics with inherent complexity in processing time-evolving data. To bridge this gap, in this paper, we propose a novel framework, called DynLLM, to deal with the dynamic graph recommendation task with LLMs. Specifically, DynLLM harnesses the power of LLMs to generate multi-faceted user profiles based on the rich textual features of historical purchase records, including crowd segments, personal interests, preferred categories, and favored brands, which in turn supplement and enrich the underlying relationships between users and items. Along this line, to fuse the multi-faceted profiles with temporal graph embedding, we engage LLMs to derive corresponding profile embeddings, and further employ a distilled attention mechanism to refine the LLM-generated profile embeddings for alleviating noisy signals, while also assessing and adjusting the relevance of each distilled facet embedding for seamless integration with temporal graph embedding from continuous time dynamic graphs (CTDGs). Extensive experiments on two real e-commerce datasets have validated the superior improvements of DynLLM over a wide range of state-of-the-art baseline methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑