简单模型在多个推荐数据集上超越复杂模型，挑战高阶序列建模必要性。
Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling?
- 用加权规则和概率转移模型替代高阶序列建模，仅依赖最近交互
- 在三个亚马逊数据集上表现优于复现的eSASRec 15%-38%
- 提醒研究者：现有基准可能无法有效衡量高阶建模的实际提升
顺序推荐系统越来越多采用语言模型架构以捕捉复杂的上下文依赖关系。然而，现有主流基准是否真的需要这种建模能力仍不明确。本文通过两种简单的、基于最近性的成对探测器——序列规则（SeqRules）和概率协同转移模型（PCTM）——进行验证，这些方法不学习高阶序列表示。在eSASRec的评估协议下，至少一种探测器在三个Amazon数据集上比我们复现的eSASRec高出15%-38%，在MovieLens-1M上高出4.4%，但在MovieLens-20M上落后27.3%。在其余四个数据集上，至少一种探测器也优于我们使用采样softmax的SASRec复现结果9%-28%。这表明，当前广泛使用的基准可能不适合衡量高阶序列建模的真实收益。更广泛地说，将Transformer模型与强的基于最近性的成对探测器对比，可为基准是否能有效评估高阶建模增益提供实证检验。
原文摘要 · Abstract (English)
Sequential recommenders increasingly use language-model architectures designed to capture complex, context-dependent interactions. Yet it remains unclear whether widely used benchmarks actually require this modelling capacity. We investigate this question using two simple, recency-weighted pairwise probes that do not learn higher-order sequence representations: Sequential Rules (SeqRules) and our Probabilistic Collaborative Transition Model (PCTM). Using the evaluation protocol of eSASRec, at least one probe exceeds our eSASRec reproduction by 15-38% on three Amazon datasets and by 4.4% on MovieLens-1M, but trails it by 27.3% on MovieLens-20M. On the four remaining datasets, at least one probe also outperforms our sampled-softmax SASRec reproduction by 9-28%, suggesting that these widely used benchmarks are poorly suited to measuring gains from higher-order sequence modelling. More broadly, comparing Transformer-based models against strong recency-weighted pairwise probes provides a concrete test of whether a benchmark can meaningfully measure gains from higher-order sequence modelling.
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。