UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation

• URL: http://arxiv.org/abs/2608.16797v1
• Date: Mon, 17 Aug 2026 16:52:56 GMT
• Title: UniDot: A Unified Network for Sequence Modeling and Feature Interaction in Large-scale Recommendation
• Abstract summary: 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.
• Score: 3.59042069607434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Industrial recommenders rely on two model families that have evolved largely independently: feature-interaction models over multi-field user/item features, and sequential models over user-behavior histories. Production systems couple them only loosely. To unify the two, we present UniDot, a novel architecture for post-click conversion prediction built from the factorization-machine (FM) point of view: the embedding inner product---which powers collaborative filtering and lets a recommender generalize to unseen user--item pairs---is the same primitive as attention's query dot key scoring, so a single dot-product of tokens can underlie both feature interaction and sequence modeling. UniDot tokenizes non-sequential fields and multi-domain behavioral sequences into one shared token space and stacks a single macro-block in which a token-mixing bus and a sequence-retrieval bus (item tokens cross-attending the histories) run in parallel and exchange state each layer through an MLP-Mixer fusion, while an FM Highway carries explicit per-layer dot-product interactions around the residual stack directly to the classifier. The sequence side is embedded once per forward pass and shared by all consumers, bounding inference latency. Trained with a dual sparse/dense (Adagrad + Muon) optimizer, an auxiliary conversion-delay head, and multi-path mutual learning, UniDot finished as the runner-up on the Industrial track of the TAAC KDD Cup 2026.

Related papers

• Topology-Masked Unified Backbone for Joint Feature Interaction and Multi-Domain Sequence Modeling [8.950162084237288]
  MaskRec is a topology-masked unified token interaction architecture for feature interaction and multi-domain sequence modeling.<n>Based on this unified token space, MaskRec designs a structured attention mask, TopoMask, which selectively enables or blocks attention connections.<n>MaskRec achieves stable improvements over the official baseline, validating the effectiveness of the proposed unified framework for industrial CVR prediction.
  arXiv  Detail & Related papers  (2026-08-27T11:49:55Z)
• 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)
• Field-Aware RankMixer with Dual-Stream Bilinear Fusion for the Tencent UNI-REC Challenge [6.560591409127247]
  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.
  arXiv  Detail & Related papers  (2026-07-17T03:22:02Z)
• OneMall: One Architecture, More Scenarios -- End-to-End Generative Recommender Family at Kuaishou E-Commerce [68.7552227901176]
  OneMall is an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou.<n>It unifies the e-commerce's multiple item distribution scenarios, such as Product-card, short-video and live-streaming.<n>OneMall has been deployed, serving over 400 million daily active users at Kuaishou.
  arXiv  Detail & Related papers  (2026-01-29T14:22:39Z)
• HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction [8.97787361529607]
  This paper presents HyFormer, a unified hybrid transformer architecture that tightly integrates long-sequence modeling and feature interaction into a single backbone.<n>Experiments on billion-scale industrial datasets demonstrate that HyFormer consistently outperforms strong LONGER and RankMixer baselines.
  arXiv  Detail & Related papers  (2026-01-19T02:55:05Z)
• MMGRec: Multimodal Generative Recommendation with Transformer Model [81.61896141495144]
  MMGRec aims to introduce a generative paradigm into multimodal recommendation. We first devise a hierarchical quantization method Graph CF-RQVAE to assign Rec-ID for each item from its multimodal information. We then train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences.
  arXiv  Detail & Related papers  (2024-04-25T12:11:27Z)
• Mixed Attention Network for Cross-domain Sequential Recommendation [63.983590953727386]
  We propose a Mixed Attention Network (MAN) with local and global attention modules to extract the domain-specific and cross-domain information. Experimental results on two real-world datasets demonstrate the superiority of our proposed model.
  arXiv  Detail & Related papers  (2023-11-14T16:07:16Z)
• AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation [80.33846577924363]
  We present All-Pairs Multi-Field Transforms (AMT), a new network architecture for video framegithub. It is based on two essential designs. First, we build bidirectional volumes for all pairs of pixels, and use the predicted bilateral flows to retrieve correlations. Second, we derive multiple groups of fine-grained flow fields from one pair of updated coarse flows for performing backward warping on the input frames separately.
  arXiv  Detail & Related papers  (2023-04-19T16:18:47Z)
• GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation [5.416421678129053]
  This paper proposes a novel sequential recommendation model called "Global Interaction Aware Multi-Interest Framework for Sequential Recommendation (GIMIRec)" The performance of GIMIRec on the Recall, NDCG and Hit Rate indicators is significantly superior to that of the state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-16T09:12:33Z)
• SWAT: Spatial Structure Within and Among Tokens [53.525469741515884]
  We argue that models can have significant gains when spatial structure is preserved during tokenization. We propose two key contributions: (1) Structure-aware Tokenization and, (2) Structure-aware Mixing.
  arXiv  Detail & Related papers  (2021-11-26T18:59:38Z)
• Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding [90.77031668988661]
  Cluster-Former is a novel clustering-based sparse Transformer to perform attention across chunked sequences. The proposed framework is pivoted on two unique types of Transformer layer: Sliding-Window Layer and Cluster-Former Layer. Experiments show that Cluster-Former achieves state-of-the-art performance on several major QA benchmarks.
  arXiv  Detail & Related papers  (2020-09-13T22:09:30Z)

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.