美团推出无需对齐输入的推荐大模型，提升工业场景扩展性。
MTFM: A Scalable and Alignment-free Foundation Model for Industrial Recommendation in Meituan
- 用异构令牌表示跨域数据，实现无对齐训练
- 用户级样本聚合使训练吞吐量显著提升
- 适合大规模工业推荐系统，可快速扩展多场景
工业推荐系统通常涉及多个场景，但现有跨域（CDR）和多场景（MSR）方法往往需要高昂资源和严格输入对齐，限制了可扩展性。我们提出MTFM（Meituan Foundation Model for Recommendation），一种基于Transformer的框架，通过将跨域数据转换为异构令牌，在无需预对齐输入的情况下捕捉多场景知识。为提升效率，我们引入用户级样本聚合，大幅降低实例总数，显著提高训练吞吐量；进一步集成分组查询注意力（Grouped-Query Attention）与定制化的混合目标注意力（Hybrid Target Attention），有效减少内存占用与计算复杂度。此外，实施内核融合及消除CPU-GPU阻塞等系统级优化，进一步提升训练与推理吞吐量。离线与在线实验验证了MTFM的有效性，表明扩大模型容量与多场景训练数据规模能带来显著性能提升。
原文摘要 · Abstract (English)
Industrial recommendation systems typically involve multiple scenarios, yet existing cross-domain (CDR) and multi-scenario (MSR) methods often require prohibitive resources and strict input alignment, limiting their extensibility. We propose MTFM (Meituan Foundation Model for Recommendation), a transformer-based framework that addresses these challenges. Instead of pre-aligning inputs, MTFM transforms cross-domain data into heterogeneous tokens, capturing multi-scenario knowledge in an alignment-free manner. To enhance efficiency, we first introduce a multi-scenario user-level sample aggregation that significantly enhances training throughput by reducing the total number of instances. We further integrate Grouped-Query Attention and a customized Hybrid Target Attention to minimize memory usage and computational complexity. Furthermore, we implement various system-level optimizations, such as kernel fusion and the elimination of CPU-GPU blocking, to further enhance both training and inference throughput. Offline and online experiments validate the effectiveness of MTFM, demonstrating that significant performance gains are achieved by scaling both model capacity and multi-scenario training data.
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。