用合成数据预训练的推荐模型，零样本推理快且省资源。
RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations
- 基于因果先验生成合成点击流数据预训练，实现快速贝叶斯推断。
- 零样本下在8个公开数据集上达到最优性能，低数据低算力下仍具竞争力。
- 适合需要轻量部署、抗领域漂移的实时推荐场景。
我们提出RecPFN，一种将上下文学习引入序列推荐的先验适配网络。RecPFN完全在从广泛结构因果先验采样的合成点击流环境中预训练，从而实现从小支持集进行贝叶斯风格推理的近似。推理时，仅需少量领域序列作为条件，轻量级解码器仅用一次前向传播即可生成查询项的下一个物品预测，无需权重更新。在八个公开基准上，RecPFN实现了零样本下的最先进性能，在低计算和低数据环境下仍显著优于监督方法。该模型部署高效，对领域漂移具有鲁棒性，优于依赖大规模真实交互数据的强零样本基线。RecPFN为可泛化、高数据效率的推荐系统提供了实用路径，并为更丰富的先验、长上下文ICL及多模态扩展开辟了新方向。代码已公开于https://github.com/SAP-samples/tabular-ai-recpfn/。
原文摘要 · Abstract (English)
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/.
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。