Unified model improves multi-scenario recommendations with feature scaling
Unified Heterogeneous Feature Interaction via Effective-Rank Scaling for Recommender Systems
Information Retrieval
Summary
Recommender systems, like those suggesting products or movies, often struggle to combine different types of information, such as user behavior and various feature data. The authors propose HiRank, a new model that merges these different data types more effectively by adjusting how the model weighs diverse information sources. This approach also tailors recommendations for different usage scenarios, improving accuracy and efficiency. Tests on big industry datasets and real user environments showed HiRank outperforms existing methods and increases user purchase rates.
What this means in practice
- •For ecommerce platform engineers: Improve recommendation quality across different shopping scenarios by integrating diverse user behaviors and feature types into a single efficient model.
- •For online content curators: Enhance personalized content delivery by jointly modeling sequential user interactions and heterogeneous content features with a unified attention mechanism.
Authors
Ao Zhang, Haochuan Li, Boya Du, Jian Yang, Qihang Fang, Yulin Xu
Abstract
Large-scale industrial ranking models must jointly capture heterogeneous feature interactions, long-term user behaviors, and multi-scenario dependencies under stringent online serving constraints. Existing architectures typically process sequential and non-sequential features with separate modules, limiting bidirectional information exchange. Directly applying homogeneous self-attention to all semantic tokens can also be inefficient when sequential and non-sequential signals exhibit different effective-ranks (eRanks). Meanwhile, shared representations can overlook scenario-specific patterns and induce negative transfer between scenarios. In this paper, we propose HiRank, a unified framework for multi-scenario recommendation that jointly models Heterogeneous feature Interactions via effective-Rank scaling. HiRank integrates gated sequential attention with heterogeneous feature interaction within a unified backbone, enabling bidirectional fusion between sequential and non-sequential representations. HiRank further uses scenario-aware aggregation to compress heterogeneous low-order tokens into a compact representation. Distinct learned projections transform the full compact representation into scenario-aware composite tokens with complementary global feature views and more uniform information density, enabling more effective high-order self-attention. Extensive experiments on industrial-scale datasets demonstrate favorable performance scaling with parameter count and consistent improvements over competitive baselines. Online A/B tests further show a 2.27% increase in orders per user.