On the Embedding Collapse when Scaling up Recommendation Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Xingzhuo, Pan, Junwei, Wang, Ximei, Chen, Baixu, Jiang, Jie, Long, Mingsheng
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Machine Learning Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Long-Sequence Recommendation Models Need Decoupled Embeddings
di: Feng, Ningya, et al.
Pubblicazione: (2024)

Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
di: Wang, Ximei, et al.
Pubblicazione: (2023)

STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
di: Su, Liangcai, et al.
Pubblicazione: (2023)

Ads Recommendation in a Collapsed and Entangled World
di: Pan, Junwei, et al.
Pubblicazione: (2024)

Towards Scalable Semantic Representation for Recommendation
di: Zhang, Taolin, et al.
Pubblicazione: (2024)

AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
di: Yang, Enneng, et al.
Pubblicazione: (2022)

ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation
di: Liu, Yuting, et al.
Pubblicazione: (2023)

Generalized Embedding Machines for Recommender Systems
di: Yang, Enneng, et al.
Pubblicazione: (2020)

Temporal Interest Network for User Response Prediction
di: Zhou, Haolin, et al.
Pubblicazione: (2023)

Understanding the Ranking Loss for Recommendation with Sparse User Feedback
di: Lin, Zhutian, et al.
Pubblicazione: (2024)

Anchored Alignment: Preventing Positional Collapse in Multimodal Recommender Systems
di: Jeong, Yonghun, et al.
Pubblicazione: (2026)

Generative Recommendation for Large-Scale Advertising
di: Xue, Ben, et al.
Pubblicazione: (2026)

Exploring Test-time Scaling via Prediction Merging on Large-Scale Recommendation
di: Lyu, Fuyuan, et al.
Pubblicazione: (2025)

Balanced Co-Clustering of Users and Items for Embedding Table Compression in Recommender Systems
di: Jiang, Runhao, et al.
Pubblicazione: (2026)

Accelerating Recommender Model Training by Dynamically Skipping Stale Embeddings
di: Maboud, Yassaman Ebrahimzadeh, et al.
Pubblicazione: (2024)

Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
di: Long, Mabiao, et al.
Pubblicazione: (2025)

Large Language Model as Universal Retriever in Industrial-Scale Recommender System
di: Jiang, Junguang, et al.
Pubblicazione: (2025)

Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
di: Xu, Cong, et al.
Pubblicazione: (2023)

Understanding DNNs in Feature Interaction Models: A Dimensional Collapse Perspective
di: Wang, Jiancheng, et al.
Pubblicazione: (2026)

Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
di: Li, Guoming, et al.
Pubblicazione: (2026)

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems
di: Chen, Xiaoshuang, et al.
Pubblicazione: (2024)

STARS: Semantic Tokens with Augmented Representations for Recommendation at Scale
di: Chen, Han, et al.
Pubblicazione: (2025)

A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems
di: Tran, Hung Vinh, et al.
Pubblicazione: (2024)

Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale
di: Hu, Zheng, et al.
Pubblicazione: (2026)

Making Recommender Systems More Knowledgeable: A Framework to Incorporate Side Information
di: Jiang, Yukun, et al.
Pubblicazione: (2024)

Unlocking the Power of Diffusion Models in Sequential Recommendation: A Simple and Effective Approach
di: Chen, Jialei, et al.
Pubblicazione: (2025)

Cold-start Recommendation by Personalized Embedding Region Elicitation
di: Nguyen, Hieu Trung, et al.
Pubblicazione: (2024)

From Feature Interaction to Feature Generation: A Generative Paradigm of CTR Prediction Models
di: Yin, Mingjia, et al.
Pubblicazione: (2025)

End-to-End Semantic ID Generation for Generative Advertisement Recommendation
di: Jiang, Jie, et al.
Pubblicazione: (2026)

Facet-Aware Multi-Head Mixture-of-Experts Model for Sequential Recommendation
di: Liu, Mingrui, et al.
Pubblicazione: (2024)

Data Efficiency for Large Recommendation Models
di: Jain, Kshitij, et al.
Pubblicazione: (2024)

A Unified Language Model for Large Scale Search, Recommendation, and Reasoning
di: De Nadai, Marco, et al.
Pubblicazione: (2026)

The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems
di: Kasalický, Petr, et al.
Pubblicazione: (2025)

RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems
di: Su, Shuo, et al.
Pubblicazione: (2024)

Evaluating Performance and Bias of Negative Sampling in Large-Scale Sequential Recommendation Models
di: Prakash, Arushi, et al.
Pubblicazione: (2024)

Macro Graph of Experts for Billion-Scale Multi-Task Recommendation
di: Yao, Hongyu, et al.
Pubblicazione: (2025)

HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
di: Liu, Yijun
Pubblicazione: (2025)

On-device Content-based Recommendation with Single-shot Embedding Pruning: A Cooperative Game Perspective
di: Tran, Hung Vinh, et al.
Pubblicazione: (2024)

Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers
di: Dong, Yue, et al.
Pubblicazione: (2025)

Are Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty
di: Li, Jiayu, et al.
Pubblicazione: (2025)