发表机构
University of Montana（蒙大拿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TailSpec-EASE提出将关系感知谱知识图谱先验注入局部闭式线性推荐，自适应长尾项目，在四个基准上以极低训练成本提升长尾与整体推荐性能。
AI 中文摘要
Web平台上的推荐系统往往过度推荐热门项目，而忽视长尾项目。项目侧知识图谱（KG），通常以链接数据或RDF风格的Web资源形式提供，可以通过共享语义属性连接稀疏项目来提供帮助。许多有竞争力的KG感知推荐器依赖图神经架构，而诸如EASE-R之类的强浅层线性模型通常忽略辅助信息，并且其全局闭式版本可能变得不可行。我们引入了TailSpec-EASE，一种轻量级推荐器，它将关系感知的谱KG先验注入到局部闭式重构目标中。先验强度适应项目流行度，为长尾项目提供更强的语义指导。在四个公开基准和广泛的经典、线性、图CF、KG感知神经和分数级KG基线中，TailSpec-EASE在整体准确性、长尾性能和训练成本之间取得了有利的权衡。与没有KG信息的对应模型相比，它将NDCG@20提高了高达24%。在配对自助法下，所有相对于无KG对应模型的长尾指标改进均具有统计显著性，并且在四个数据集中的三个上，整体NDCG显著提高。在一项具有代表性的Amazon-book计时研究中，TailSpec-EASE在CPU上训练耗时37秒，而GPU训练的KGAT运行耗时2,584秒，CPU LightGCN耗时15,800秒，同时在该数据集上实现了更高的NDCG@20和Tail Recall@20。它还在全局闭式模型内存不足的目录上保持可行。
英文摘要
Recommender systems on Web platforms tend to over-serve popular items and neglect the long tail. Item-side knowledge graphs (KGs), often available as linked data or RDF-style Web resources, can help by connecting sparse items through shared semantic attributes. Many competitive KG-aware recommenders rely on graph neural architectures, whereas strong shallow linear models such as EASE-R typically ignore side information and may become infeasible in their global closed-form version. We introduce TailSpec-EASE, a lightweight recommender that injects a relation-aware spectral KG prior into a local closed-form reconstruction objective. The prior strength adapts to item popularity, giving stronger semantic guidance to long-tail items. Across four public benchmarks and a broad set of classical, linear, graph-CF, KG-aware neural, and score-level KG baselines, TailSpec-EASE attains a favorable trade-off between overall accuracy, long-tail performance, and training cost. It improves NDCG@20 by up to 24% over its counterpart without KG information. All tail-metric improvements over the no-KG counterpart are statistically significant under a paired bootstrap, and overall NDCG improves significantly on three of the four datasets. In a representative Amazon-book timing study, TailSpec-EASE trains in 37 seconds on CPU, compared with 2,584 seconds for a GPU-trained KGAT run and 15,800 seconds for CPU LightGCN, while attaining higher NDCG@20 and Tail Recall@20 on that dataset. It also remains feasible on catalogs where the global closed-form model runs out of memory.
CommentsAccepted at the main research track of WISE 2026 (26th International Conference on Web Information Systems Engineering)
