This paper presents STAR (Structured Tokenization and Target-Aware Interest Representation), a practical framework for the KDD Cup 2026 Tencent UniRec Challenge that combines structured feature tokenization with target-aware interest representation on top of a HyFormer-style multi-sequence backbone.
Abstract
Post-click conversion rate (PCVR) prediction is a core ranking task in industrial recommender systems. Modern ranking models must jointly capture heterogeneous non-sequential features, multi-behavior user sequences, and target-item-aware user interests, while remaining robust to high-cardinality sparse features, missing values, and train-inference inconsistencies. In this paper, we present STAR (Structured Tokenization and Target-Aware Interest Representation), a practical framework for the KDD Cup 2026 Tencent UniRec Challenge. STAR combines structured feature tokenization with target-aware interest representation on top of a HyFormer-style multi-sequence backbone. It introduces high-cardinality signal recovery, explicit user-item interaction tokens, target-aware sequence decoding, and a weighted user-item contrastive auxiliary objective inspired by InfoNCE. We further align the training and inference pipelines by reconstructing feature remapping tables and structural hyperparameters from the saved training configuration. Experiments on the challenge dataset identify the components that most reliably improve ranking AUC, while LogLoss is reported as a calibration diagnostic. The main ablation study shows a large gain from temporal context, with smaller but useful contributions from contrastive alignment, target-aware interest encoding, and high-cardinality sequence feature recovery.
PALRec is proposed, a parameter-preserving augmentation framework that equips an LLM with recommendation capabilities while keeping its original parameters fixed and consistently outperforms fully fine-tuned counterparts in recommendation accuracy while preserving the LLM’s pre-trained knowledge.
Hyunsoo Na, Minseok Gang, Sang-goo Lee et al.· ACM Transactions on Informat...· 0 citations
Ultra-long user history modeling has been a highly effective approach in modern industrial recommendation systems, with most works heavily utilizing search-based methods and summarization based methods to map massive user interaction logs into latent user representation with algorithm designs to address the scaling cha...
Yuan-Zheng Lin, Diego Uribe Mora, Yuan Shao et al.· Proceedings of the 20th ACM...· 0 citations
Industrial ranking models for recommendation have scaled feature interaction and sequence modeling separately; recent architectures such as HyFormer and MixFormer unify both in a stackable backbone. Real-world recommender systems, however, nearly always require multi-task learning, yet existing unified architectures co...
Yu-Chen Wang, Feng-Nan Niu, Qing Tan et al.· 0 citations
The Fusion of Layer-wise Exits for Sequential Recommendation (FLEXRec), a discriminative framework that enhances compact LLMs while retaining scalable full-corpus ranking and achieves state-of-the-art accuracy among competing methods while remaining highly efficient.
Xurong Liang, Tong Chen, Q. Nguyen et al.· 0 citations
The Hierarchical Semantic Interest Evolution Network (HSIEN), a novel generative-discriminative framework that significantly alleviates modality misalignment and enhances CTR prediction performance through feature complementarity, is proposed.
Yi-Fan Cao, Rui Wu, Xiang Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
Difficulty-Aware Semantic-ID Optimization (DASO), a tree-aware post-training method that addresses failure mode as an online rollout-allocation problem and improves over MiniOneRec-style GRPO on 11 of 12 metrics and achieves the best result on 9 of 12 metrics.
Xin Yu, Stephen Li, S. Aghaei et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.