用图拉普拉斯位置嵌入增强序列推荐
Enriching Sequential Recommendation with Graph Laplacian Positional Embeddings
- HSE University（高等经济大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出用图拉普拉斯位置嵌入替代序列推荐中的可学习位置嵌入，在SASRec上构建物品共现图并利用其特征向量，实验表明该方法在多个基准上提升性能，证明图结构可有效替代顺序编码。
AI中文摘要：
序列推荐器通常依赖可学习的位置嵌入来编码用户交互的顺序。在这项工作中，我们探讨这种顺序信号是否可以被从物品空间导出的结构信号所替代。我们提出在SASRec中使用拉普拉斯位置嵌入：我们从训练交互中构建物品共现图，计算其对称归一化拉普拉斯矩阵的特征向量，并将其用作冻结的图派生位置嵌入。骨干架构和训练目标保持不变。在四个公开的序列推荐基准上的实验表明，这种简单的替换在大多数排名指标上提升了SASRec的性能，并且与强位置和时间编码基线相比仍具有竞争力。这些发现表明，物品-物品图结构可以成为序列推荐中标准顺序位置嵌入的有效替代。
英文摘要：
Sequential recommenders typically rely on learnable positional embeddings to encode the order of user interactions. In this work, we ask whether this ordinal signal can be replaced by a structural one derived from the item space. We propose to use Laplacian positional embeddings in SASRec: we build an item co-occurrence graph from training interactions, compute eigenvectors of its symmetric normalized Laplacian, and use them as frozen graph-derived positional embeddings. The backbone architecture and training objective remain unchanged. Experiments on four public sequential-recommendation benchmarks show that this simple replacement improves SASRec performance on most ranking metrics and remains competitive with strong positional and temporal encoding baselines. These findings indicate that item-item graph structure can be an effective substitute for standard ordinal positional embeddings in sequential recommendation.
