11. Recommender System

Recommender systems serve as intelligent agents, offering suggestions for items most relevant to a specific user. To do so, they scrutinize data items such as user characteristics, item features, and the interactions between the two. Over the past few years, powerhouse companies like Google, Facebook, and Alibaba have harnessed deep learning technologies to enhance the capabilities of recommender models. By deploying deep learning methodologies, these systems are endowed with the capability to effectively learn from data through gradient-based methods. Moreover, these systems are able to exploit large neural networks, including transformers and emerging large language models. This, in turn, bolsters the system’s proficiency in dissecting complex, multi-modal data.

In this chapter, we will delve into the foundational elements of deep learning recommender systems (DLRSs). We will elucidate key operational processes within these systems, primarily focusing on the multi-stage generation of recommendations and the updating of model parameters. Lastly, we will delve into a real-world recommender system, shedding light on strategic approaches used to tackle practical challenges.

This chapter has the following learning objectives:

1. Understand the architecture of a recommender system and its essential components.

2. Understand multi-stage recommendation and model update in a recommender system.

3. Attain insights into the challenges faced by practical recommender systems and discover their corresponding solutions.

• 11.1. Overview
• 11.2. System Components
  • 11.2.1. Message Queue
  • 11.2.2. Feature Store
  • 11.2.3. Neural Networks
  • 11.2.4. Embedding Table
  • 11.2.5. Parameter Server
  • 11.2.6. Training Server
  • 11.2.7. Inference Server
• 11.3. Recommendation Pipeline
  • 11.3.1. Retrieval Stage
  • 11.3.2. Ranking Stage
  • 11.3.3. Ranking with Deep Learning
• 11.4. Model Update
  • 11.4.1. Necessity for Model Updates
  • 11.4.2. Offline Process of Model Update
  • 11.4.3. Needs for Low-latency Model Updates
• 11.5. Supporting Real-time Machine Learning
  • 11.5.1. System Challenges
  • 11.5.2. Application-Specific Synchronization Protocols
  • 11.5.3. Application-Aware Model Update Scheduling
  • 11.5.4. Online Model State Management
• 11.6. Chapter Summary
• 11.7. Further Reading