AI 中文总结
研究针对生成式推荐中NTP的时间和空间局部性局限，提出NONTP。通过TCL和TDL两个辅助目标扩展训练信号覆盖范围，在多数据集实验中显著提升推荐指标，消融研究明确各组件贡献，为推荐系统发展提供新思路。
AI 中文摘要
下一个token预测（NTP）存在两个结构训练信号限制。首先，NTP仅针对单步预测进行优化，对学习更长范围的行为结构没有监督压力，即时间局部性。其次，在多域序列中，每个目标项嵌入仅从紧接的前一个隐藏状态接收梯度更新，没有来自跨域上下文的显式梯度路径，即空间局部性。我们提出了NONTP，通过两个辅助目标在两个维度上扩展NTP的信号覆盖范围。时间对比学习（TCL）使用带有InfoNCE的BYOL风格的指数移动平均（EMA）教师，在表示空间中将隐藏状态与K步未来轨迹对齐。跨域学习（TDL）对跨域隐藏状态进行平均池化，并通过共享预测头进行预测，开辟了第二条无额外参数成本的梯度路径。在推理时两者都被丢弃，无额外开销。在一个四域美团工业数据集（全排序）上，NONTP比NTP的HR@10提高了 +34.3%，比MBGR提高了 +18.3%。在公共亚马逊电影 - 书籍 - CD基准上，HR@10提高了 +2.8%，NDCG@10提高了 +3.7%。在线A/B测试证实点击率提高了 +1.8%，商品交易总额提高了 +2.1%（两者p < 0.01）。消融研究证实每个组件都有独立贡献，并将梯度冲突作为未来工作的一个方向进行了分析。
英文摘要
Next-Token Prediction (NTP) carries two structural training signal limitations. First, NTP optimizes for single-step prediction only, placing no supervised pressure on learning longer-range behavioral structure -- we term this \textbf{temporal locality}. Second, in multi-domain sequences, each target item embedding receives gradient updates exclusively from the immediately preceding hidden state, with no explicit gradient pathway from cross-domain context -- we term this \textbf{spatial locality}. We propose \textbf{NONTP}, extending NTP's signal coverage along both dimensions through two auxiliary objectives. \textbf{TCL (Temporal Contrastive Learning)} uses a BYOL-style EMA teacher with InfoNCE to align hidden states against a $K$-step future trajectory in representation space. \textbf{TDL (Trans-Domain Learning)} mean-pools cross-domain hidden states and predicts through the shared prediction head, opening a second gradient pathway with no additional parameters. Both are discarded at inference: zero overhead. On a four-domain Meituan industrial dataset (full ranking), NONTP achieves HR@10 +34.3\% over NTP and +18.3\% over MBGR. On the public Amazon Movie-Book-CDs benchmark, HR@10 +2.8\% and NDCG@10 +3.7\%. Online A/B tests confirm CTR +1.8\% and GMV +2.1\% (both $p < 0.01$). Ablation studies confirm each component contributes independently, with gradient conflict analyzed as a direction for future work.
