针对广告点击率预测，提出双流融合的注意力模型。
Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge
- 分域建模用户行为序列，分离近期与早期兴趣。
- 通过双流结构融合深层与浅层特征表示，提升预测精度。
- 适合多领域推荐系统研发者参考使用。
本文介绍我们对 KDD Cup 2026 腾讯 UNIREC 挑战赛的解决方案。任务要求联合建模多领域用户行为序列与非序列多字段特征，以预测目标广告的点击率（pCVR）。我们提出一种场感知的 RankMixer（FA-RankMixer）模型，采用双流双线性融合机制。模型首先使用目标感知的 DIN 模块从多个行为域中提取用户兴趣，并对最长行为序列分别建模近期与早期兴趣。随后，基于特征域与行为域生成语义令牌，通过 RankMixer 块实现跨令牌交互。同时引入浅层 MLP 流与深层 RankMixer 流，并通过分组双线性模块融合两者表示。最终方案在官方排行榜上位列第九。代码已开源：https://github.com/PixelCookie-zyf/TAAC-2026-SeRankMixer。
原文摘要 · Abstract (English)
This paper presents our solution to the KDD Cup 2026 Tencent UNIREC Challenge. The task requires joint modeling of multi-domain user behavior sequences and non-sequential multi-field features for target-ad pCVR prediction. We develop a Field-Aware RankMixer (FA-RankMixer) with dual-stream bilinear fusion. The model first applies target-aware DIN modules to extract user interests from multiple behavior domains. It also models recent and earlier interests separately for the longest behavior sequence. The model then forms semantic tokens based on feature fields and behavior domains and uses RankMixer blocks for cross-token interaction. A shallow MLP stream complements the deep RankMixer stream, and a group-wise bilinear module fuses their representations. Our final solution ranks ninth on the official leaderboard. Our code is available at https://github.com/PixelCookie-zyf/TAAC-2026-SeRankMixer.
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。