Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge

• URL: http://arxiv.org/abs/2607.15590v1
• Date: Fri, 17 Jul 2026 03:22:02 GMT
• Title: Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge
• Abstract summary: This paper presents our solution to the KDD Cup 2026 Tencent UNIREC Challenge.<n>The task requires joint modeling of multi-domain user behavior sequences.<n>We develop a Field-Aware RankMixer with dual-stream bilinear fusion.
• Score: 6.560591409127247
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation [3.59042069607434]
  We present UniDot, a novel architecture for post-click conversion prediction built from the factorization-machine point of view.<n>A single dot-product of tokens can underlie both feature interaction and sequence modeling.<n>UniDot finished as the runner-up on the Industrial track of the TAAC KDD Cup 2026.
  arXiv  Detail & Related papers  (2026-08-17T16:52:56Z)
• RoleMix: Unifying Sequential and Non-Sequential Features via Semantic Tokenization for Post-Click Conversion Rate Prediction [1.6050320174037502]
  RoleMix represents sequential and non-sequential evidence through a shared, role-preserving token interface.<n>On the large-scale KDD Cup 2026 Tencent UniRec Challenge, RoleMix achieves 83.648% online AUC, outperforming the official industrial baseline by 1.953%.
  arXiv  Detail & Related papers  (2026-07-18T15:44:48Z)
• DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models [47.963203679519744]
  DiffRetriever is a representative-token retriever for diffusion language models.<n>It appends K masked positions to the prompt and reads all K in a single bidirectional forward pass.<n>We show that the bottleneck is sequential generation, not the multi-token idea itself.
  arXiv  Detail & Related papers  (2026-05-08T03:57:51Z)
• SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting [9.398256560898448]
  SEMixer is a lightweight model designed for long-term time series forecasting (TSF)<n>Mixer features a Random Attention Mechanism (RAM) and a Multiscale Progressive Mixing Chain (MPMC)<n>MPMC stacks RAM and ensemble-Mixer in a memory-efficient manner, achieving more effective temporal mixing.
  arXiv  Detail & Related papers  (2026-02-18T06:53:32Z)
• LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training [53.539682966282534]
  Cross-domain Sequential Recommendation (CDSR) has been proposed to enrich user-item interactions by incorporating information from various domains.<n>Despite current progress, the imbalance issue and transition issue hinder further development of CDSR.<n>We propose an LLMs Enhanced Cross-domain Sequential Recommendation with Dual-phase Training (LLM-EDT)
  arXiv  Detail & Related papers  (2025-11-25T05:18:04Z)
• RankMixer: Scaling Up Ranking Models in Industrial Recommenders [25.072128027628104]
  Training and serving cost on industrial Recommenders must respect strict latency bounds and high QPS demands.<n>We introduce RankMixer, a hardware-aware model design tailored towards a unified and scalable feature-interaction architecture.<n> Experiments show RankMixer's superior scaling abilities on a trillion-scale production dataset.
  arXiv  Detail & Related papers  (2025-07-21T12:28:55Z)
• Leveraging Multimodal Data and Side Users for Diffusion Cross-Domain Recommendation [23.27301183474805]
  Cross-domain recommendation (CDR) aims to address the persistent cold-start problem in Recommender Systems.<n>We propose a model leveraging Multimodal data and Side users for diffusion Cross-domain recommendation (MuSiC)<n>MuSiC achieves state-of-the-art performance, significantly outperforming all selected baselines.
  arXiv  Detail & Related papers  (2025-07-05T10:57:29Z)
• Semantic Gaussian Mixture Variational Autoencoder for Sequential Recommendation [49.492451800322144]
  We propose a novel VAE-based Sequential Recommendation model named SIGMA.<n>For multi-interest elicitation, SIGMA includes a probabilistic multi-interest extraction module.<n>Experiments on public datasets demonstrate the effectiveness of SIGMA.
  arXiv  Detail & Related papers  (2025-02-22T08:29:52Z)
• Multi-granularity Interest Retrieval and Refinement Network for Long-Term User Behavior Modeling in CTR Prediction [68.90783662117936]
  Click-through Rate (CTR) prediction is crucial for online personalization platforms.<n>Recent advancements have shown that modeling rich user behaviors can significantly improve the performance of CTR prediction.<n>We propose Multi-granularity Interest Retrieval and Refinement Network (MIRRN)
  arXiv  Detail & Related papers  (2024-11-22T15:29:05Z)
• Learning with MISELBO: The Mixture Cookbook [62.75516608080322]
  We present the first ever mixture of variational approximations for a normalizing flow-based hierarchical variational autoencoder (VAE) with VampPrior and a PixelCNN decoder network. We explain this cooperative behavior by drawing a novel connection between VI and adaptive importance sampling. We obtain state-of-the-art results among VAE architectures in terms of negative log-likelihood on the MNIST and FashionMNIST datasets.
  arXiv  Detail & Related papers  (2022-09-30T15:01:35Z)
• MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks [97.08677678499075]
  We introduce MixMo, a new framework for learning multi-input multi-output deepworks. We show that binary mixing in features - particularly with patches from CutMix - enhances results by makingworks stronger and more diverse. In addition to being easy to implement and adding no cost at inference, our models outperform much costlier data augmented deep ensembles.
  arXiv  Detail & Related papers  (2021-03-10T15:31:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.