用于腾讯 UNI-REC 挑战赛的双流双线性融合场感知排序混合器
Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge
- Meituan（美团）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对腾讯 UNIREC 挑战赛中多域用户行为序列和多字段特征联合建模预测目标广告 pCVR 的任务，提出带双流双线性融合的场感知排序混合器，经实验在官方排行榜排第九。
AI中文摘要：
本文介绍了我们对 2026 年 KDD 杯腾讯 UNIREC 挑战赛的解决方案。该任务要求对多域用户行为序列和非序列多字段特征进行联合建模，以预测目标广告的 pCVR。我们开发了一种具有双流双线性融合的场感知排序混合器（FA-RankMixer）。该模型首先应用目标感知 DIN 模块从多个行为域中提取用户兴趣。它还分别对最长行为序列的近期和早期兴趣进行建模。然后基于特征字段和行为域形成语义令牌，并使用排序混合器块进行跨令牌交互。一个浅层 MLP 流补充深度排序混合器流，一个分组双线性模块融合它们的表示。我们的最终解决方案在官方排行榜上排名第九。我们的代码可在此 https URL 上获取。
英文摘要：
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.
