10 papers
MixFormer: Co-Scaling Up Dense and Sequence in Industrial Recommenders
Xu Huang, Hao Zhang, Zhifang Fan +6
As industrial recommender systems enter a scaling-driven regime, Transformer architectures have become increasingly attractive for scaling models towards larger capacity and longer…
Compute Only Once: UG-Separation for Efficient Large Recommendation Models
Hui Lu, Zheng Chai, Shipeng Bai +15
Driven by scaling laws, recommender systems increasingly rely on larger-scale models to capture complex feature interactions and user behaviors, but this trend also leads to prohib…
TokenMixer-Large: Scaling Up Large Ranking Models in Industrial Recommenders
Yuchen Jiang, Jie Zhu, Xintian Han +18
While scaling laws for recommendation models have gained significant traction, existing architectures such as Wukong, HiFormer and DHEN, often struggle with sub-optimal designs and…
MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation
Shikang Wu, Hui Lu, Jinqiu Jin +9
Scaling deep learning recommendation models is an effective way to improve model expressiveness. Existing approaches often incur substantial computational overhead, making them dif…
HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction
Yunwen Huang, Shiyong Hong, Xijun Xiao +7
Industrial large-scale recommendation models (LRMs) face the challenge of jointly modeling long-range user behavior sequences and heterogeneous non-sequential features under strict…
LongRetriever: Towards Ultra-Long Sequence based Candidate Retrieval for Recommendation
Qin Ren, Zheng Chai, Xijun Xiao +2
Precisely modeling user ultra-long sequences is critical for industrial recommender systems. Current approaches predominantly focus on leveraging ultra-long sequences in the rankin…