HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915814133727232 |
|---|---|
| author | Yuan, Kun Bi, Junyu Cheng, Daixuan Wu, Changfa Xiao, Shuwen Cao, Binbin Wu, Jian Jiang, Yuning |
| author_facet | Yuan, Kun Bi, Junyu Cheng, Daixuan Wu, Changfa Xiao, Shuwen Cao, Binbin Wu, Jian Jiang, Yuning |
| contents | Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_21009 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders Yuan, Kun Bi, Junyu Cheng, Daixuan Wu, Changfa Xiao, Shuwen Cao, Binbin Wu, Jian Jiang, Yuning Information Retrieval Computation and Language Modern recommender systems leverage ultra-long user behavior sequences to capture dynamic preferences, but end-to-end modeling is infeasible in production due to latency and memory constraints. While summarizing history via interest centers offers a practical alternative, existing methods struggle to (1) identify user-specific centers at appropriate granularity and (2) accurately assign behaviors, leading to quantization errors and loss of long-tail preferences. To alleviate these issues, we propose Hierarchical Sparse Activation Compression (HiSAC), an efficient framework for personalized sequence modeling. HiSAC encodes interactions into multi-level semantic IDs and constructs a global hierarchical codebook. A hierarchical voting mechanism sparsely activates personalized interest-agents as fine-grained preference centers. Guided by these agents, Soft-Routing Attention aggregates historical signals in semantic space, weighting by similarity to minimize quantization error and retain long-tail behaviors. Deployed on Taobao's "Guess What You Like" homepage, HiSAC achieves significant compression and cost reduction, with online A/B tests showing a consistent 1.65% CTR uplift -- demonstrating its scalability and real-world effectiveness. |
| title | HiSAC: Hierarchical Sparse Activation Compression for Ultra-long Sequence Modeling in Recommenders |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2602.21009 |