ChronicleRec：面向终身用户建模的预训练时间锚定令牌
ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling
浏览论文内容
中文总结 AI 辅助
ChronicleRec通过预训练时间锚定令牌，将超长用户行为序列压缩为有序摘要，解耦终身建模与在线评分，在工业推荐中提升效果。
中文摘要 AI 辅助
对超长用户行为序列进行建模对于工业推荐和在线广告至关重要，然而直接将数千条历史行为输入排序模型在计算上代价高昂，而截断则会丢失长程信号。现有的终身兴趣方法为每个候选行为检索与目标相关的行为，将长序列建模与候选评分耦合，并产生重复的在线成本。近期与目标无关的压缩方法能够实现用户摘要的缓存，但往往在序列末尾追加查询令牌并使用双向编码，产生无序且冗余的摘要，忽略了时间结构。我们提出ChronicleRec，一个预训练-迁移框架，将超长行为序列一次性压缩为一组按时间顺序排列的Chronicle令牌。ChronicleRec采用感知近期性的多粒度合并，保留近期行为的同时对远期历史进行粗化。随后，它将查询令牌与合并后的序列交错排列，并使用因果编码器，使每个查询仅汇总其时间锚点之前的历史。多视界设计在不同并行分支上掩码不同的近期历史窗口，以学习互补的长程兴趣。压缩器通过掩码-预测目标进行预训练，从压缩的较旧历史中重建被保留的近期行为，将历史信号与近当前意图对齐。由于Chronicle令牌与目标无关，它们可以按用户缓存，从而将超长序列建模与在线候选评分解耦。在KuaiRand和Tencent AdLive上的实验表明，ChronicleRec优于近期窗口和单遍压缩基线，同时接近全注意力性能。令牌分析揭示了时间组织和互补的表示，为期七天的在线A/B测试确认了显著的生产收益。
英文摘要
Modeling ultra-long user behavior sequences is crucial for industrial recommendation and online advertising, yet directly feeding thousands of historical actions into ranking models is computationally prohibitive, while truncation discards long-range signals. Existing lifelong-interest methods retrieve target-relevant behaviors for each candidate, coupling long-sequence modeling with candidate scoring and repeated online cost. Recent target-independent compression methods enable cached user summaries, but often append query tokens at the sequence end and use bidirectional encoding, producing unordered and redundant summaries that overlook temporal structure. We propose ChronicleRec, a pre-train-and-transfer framework that compresses an ultra-long behavior sequence once into a chronologically ordered set of Chronicle Tokens. ChronicleRec applies a recency-aware multi-granularity merge, preserving recent behaviors while coarsening distant history. It then interleaves query tokens with the merged sequence and uses a causal encoder, so each query summarizes only the history before its temporal anchor. A multi-horizon design masks different recent-history windows across parallel branches to learn complementary long-range interests. The compressor is pre-trained with a mask-and-predict objective that reconstructs held-out recent behaviors from compressed older history, aligning historical signals with near-present intent. Since Chronicle Tokens are target-independent, they can be cached per user, decoupling ultra-long sequence modeling from online candidate scoring. Experiments on KuaiRand and Tencent AdLive show that ChronicleRec outperforms recent-window and single-pass compression baselines while approaching full-attention performance. Token analyses reveal temporally organized and complementary representations, and a seven-day online A/B test confirms significant production gains.
