发表机构
SAP SE（思爱普公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RecPFN是一种将上下文学习引入序列推荐的先验拟合网络，经合成点击流环境预训练，在八个基准测试中实现最优零样本性能，部署高效且鲁棒，为通用推荐系统提供新路径。
AI 中文摘要
我们提出RecPFN，一种将上下文学习（in-context learning）引入序列推荐的先验拟合网络（prior-fitted network）。RecPFN完全在从广泛的结构因果先验（structural causal prior）中采样的合成点击流环境上进行预训练，使其能够对来自小支持集的贝叶斯风格推断进行摊销。在推理阶段，一个轻量级的仅解码器Transformer以少量领域序列为条件，通过单次前向传播生成对查询的下一个项目预测，无需任何权重更新。在八个公共基准测试中，RecPFN实现了最先进的零样本（zero-shot）性能，同时在低计算量和低数据 regime下与监督方法保持强劲竞争力。它部署高效且对领域转移（domain shift）具有鲁棒性，优于依赖大型真实交互语料库的强大零样本基线。RecPFN为通用、数据高效的推荐系统提供了实用路径，并为更丰富的先验、更长上下文的ICL以及多模态扩展开辟了途径。训练和评估代码可在该https URL获取。
英文摘要
We introduce RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation. RecPFN is pretrained entirely on synthetic clickstream environments sampled from a broad structural causal prior, enabling it to amortize Bayesian-style inference from a small support set. At inference, a lightweight decoder-only transformer conditions on a handful of domain sequences and produces next-item predictions for queries in a single forward pass, without any weight updates. Across eight public benchmarks, RecPFN achives state-of-the-art zero-shot performance while remaining strongly competitive with supervised methods in low-compute and low-data regimes. It is deployment-efficient and robust to domain shift, outperforming strong zero-shot baselines that rely on large real-interaction corpora. RecPFN provides a practical path toward generalizable, data-efficient recommenders and opens avenues for richer priors, longer-context ICL, and multimodal extensions. Code for training and evaluation is publicly available at https://github.com/SAP-samples/tabular-ai-recpfn/.
Comments12 pages, 4 figures, 8 tables
Journal refIn Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1731-1742. 2026
