Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-intent Aware Contrastive Learning for Sequential Recommendation

Junshu Huang, Zi Long, Xianghua Fu, Yin Chen

TL;DR

SR models considering multi-intent information in their framework are more likely to reflect real-life recommendation scenarios accurately and oversimplifies real-world recommendation scenarios accurately.

Abstract

Intent is a significant latent factor influencing user-item interaction sequences. Prevalent sequence recommendation models that utilize contrastive learning predominantly rely on single-intent representations to direct the training process. However, this paradigm oversimplifies real-world recommendation scenarios, attempting to encapsulate the diversity of intents within the single-intent level representation. SR models considering multi-intent information in their framework are more likely to reflect real-life recommendation scenarios accurately.

Multi-intent Aware Contrastive Learning for Sequential Recommendation

TL;DR

SR models considering multi-intent information in their framework are more likely to reflect real-life recommendation scenarios accurately and oversimplifies real-world recommendation scenarios accurately.

Abstract

Intent is a significant latent factor influencing user-item interaction sequences. Prevalent sequence recommendation models that utilize contrastive learning predominantly rely on single-intent representations to direct the training process. However, this paradigm oversimplifies real-world recommendation scenarios, attempting to encapsulate the diversity of intents within the single-intent level representation. SR models considering multi-intent information in their framework are more likely to reflect real-life recommendation scenarios accurately.
Paper Structure (23 sections, 16 equations, 3 figures, 2 tables)

This paper contains 23 sections, 16 equations, 3 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Sequential Recommendation
  4. Contrastive SSL for SR
  5. Latent Intent for Recommendation
  6. PRELIMINARIES
  7. Problem Definition
  8. Next Item Prediction
  9. Contrastive Learning in SR
  10. THE PROPOSED METHOD
  11. Intent-aware User Representation
  12. Multi-intent Aware Contrastive Learning
  13. Multi-task Learning
  14. EXPERIMENTS
  15. Experimental Setting
  16. ...and 8 more sections

Figures (3)

  • Figure 1: The figure demonstrates the variation in candidate item propensity when the training of SR models is guided by single-intent or multi-intent information. Items in the sequence of User2 that are identical to those of user1 have been highlighted with a blue background.
  • Figure 2: Overall framework.
  • Figure 3: Performance comparison w.r.t. hyper-parameters $K$ and $R/K$.