研究人员发布了一项关于行为基础模型规模法则的研究。这类模型在用户事件序列上进行训练，应用于推荐和欺诈检测等场景。研究发现，一个包含约2%参数的更小嵌入器在各种训练预算下都是计算最优的。最优训练策略在较低计算水平下倾向于更侧重数据，而在计算增加时则趋近于Chinchilla启发式。 AI
影响 确定了行为基础模型的最佳参数分配和训练策略，可能指导未来的开发和资源分配。
排序理由 该集群包含一篇详细介绍行为基础模型规模法则研究结果的研究论文。
在 arXiv cs.IR (Information Retrieval) 阅读 →
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.05257v1 Announce Type: new Abstract: Foundation models are increasingly trained on sequences of user actions in recommendation, payments, fraud, and commerce, but these models still lack the kind of compute calibration that scaling laws provide for language models. We …
Foundation models are increasingly trained on sequences of user actions in recommendation, payments, fraud, and commerce, but these models still lack the kind of compute calibration that scaling laws provide for language models. We study a common two-part behavioral-model archite…