MSN: A Memory-based Sparse Activation Scaling Framework for Large-scale Industrial Recommendation
cs.IR
Submitted: 2026-02-07
Updated: 2026-11-14
Terminology
Sources
- Layer Normalization
- Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
- Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems
- LEMUR: Large scale End-to-end MUltimodal Recommendation
- Mixture of A Million Experts
- HyFormer: Revisiting the Roles of Sequence Modeling and Feature Interaction in CTR Prediction
- Realizing Scaling Laws in Recommender Systems: A Foundation-Expert Paradigm for Hyperscale Model Deployment
- MTmixAtt: Integrating Mixture-of-Experts with Multi-Mix Attention for Large-Scale Recommendation
- Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy
- A Survey of Large Language Models
Related papers
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
- One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations