mlsanityData to 7 Oct 2026

Monolith: Real Time Recommendation System With Collisionless Embedding Table

arXiv 2209.07663 ↗First posted 16 Sep 2022cs.IRcited by 30

Not on the map. Why?

Abstract (arXiv)

Building a scalable and real-time recommendation system is vital for many businesses driven by time-sensitive customer feedback, such as short-videos ranking or online ads. Despite the ubiquitous adoption of production-scale deep learning frameworks like TensorFlow or PyTorch, these general-purpose frameworks fall short of business demands in recommendation scenarios for various reasons: on one hand, tweaking systems based on static parameters and dense computations for recommendation with dynamic and sparse features is detrimental to model quality; on the other hand, such frameworks are designed with batch-training stage and serving stage completely separated, preventing the model from interacting with customer feedback in real-time. These issues led us to reexamine traditional approaches and explore radically different design choices. In this paper, we present Monolith, a system tailored for online training. Our design has been driven by observations of our application workloads and production environment that reflects a marked departure from other recommendations systems. Our contributions are manifold: first, we crafted a collisionless embedding table with optimizations such as expirable embeddings and frequency filtering to reduce its memory footprint; second, we provide an production-ready online training architecture with high fault-tolerance; finally, we proved that system reliability could be traded-off for real-time learning. Monolith has successfully landed in the BytePlus Recommend product.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2022.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 13; 2026: 6.

30 papers.

Sort:

By area:

  1. 2024Wukong: Towards a Scaling Law for Large-Scale Recommendationcited by 72
  2. 2025PLUM: Adapting Pre-trained Language Models for Industrial-scale Generative Recommendationscited by 27
  3. 2023High-Throughput Vector Similarity Search in Knowledge Graphscited by 19
  4. 2025Enhancing Embedding Representation Stability in Recommendation Systems with Semantic IDcited by 19
  5. 2024SUBER: An RL Environment with Simulated Human Behavior for Recommender Systemscited by 11
  6. 2024Jump Starting Bandits with LLM-Generated Prior Knowledgecited by 11
  7. 2023Online Matching: A Real-time Bandit System for Large-scale Recommendationscited by 8
  8. 2025Reinforcement Learning from User Feedbackcited by 8
  9. 2025Quake: Adaptive Indexing for Vector Searchcited by 8
  10. 2025Martingale Posterior Neural Networks for Fast Sequential Decision Makingcited by 4
  11. 2024UnifiedRL: A Reinforcement Learning Algorithm Tailored for Multi-Task Fusion in Large-Scale Recommender Systemscited by 2
  12. 2024Dynamic User Interest Augmentation via Stream Clustering and Memory Networks in Large-Scale Recommender Systemscited by 2
18 more
  1. 2024LiNR: Model Based Neural Retrieval on GPUs at LinkedIncited by 2
  2. 2025xGR: Efficient Generative Recommendation Serving at Scalecited by 2
  3. 2023Content-based Recommendation Engine for Video Streaming Platformcited by 1
  4. 2025Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterestcited by 1
  5. 2025Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updatescited by 1
  6. 2026RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecyclecited by 1
  7. 2024EnhancedRL: An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Recommender Systemscited by 0
  8. 2024CUPID: A Real-Time Session-Based Reciprocal Recommendation System for a One-on-One Social Discovery Platformcited by 0
  9. 2025Accelerating Recommender Model ETL with a Streaming FPGA-GPU Dataflowcited by 0
  10. 2025DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendationcited by 0
  11. 2025Weightless Neural Networks for Continuously Trainable Personalized Recommendation Systemscited by 0
  12. 2025Efficient Hyperparameter Search for Non-Stationary Model Trainingcited by 0
  13. 2025Inference Time Feature Injection: A Lightweight Approach for Real-Time Recommendation Freshnesscited by 0
  14. 2026Multi-Probe Zero Collision Hash (MPZCH): Mitigating Embedding Collisions and Enhancing Model Freshness in Large-Scale Recommenderscited by 0
  15. 2026SURGE: SuperBatch Unified Resource-efficient GPU Encoding for Heterogeneous Partitioned Datacited by 0
  16. 2026A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systemscited by 0
  17. 2026Mutable Low-Rank Sketches for Retrain-Free Recommendationcited by 0
  18. 2026TopGQ: Fast GNN Post-Training Quantization Leveraging Topology Informationcited by 0