Intent Contrastive Learning for Sequential Recommendation

By Yongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, Caiming Xiong. The Web Conference, 2022

463 citations recorded by the source corpus.

Users’ interactions with items are driven by various intents (e.g., preparing for holiday gifts, shopping for fishing equipment, etc.). However, users’ underlying intents are often unobserved/latent, making it challenging to leverage such latent intents for Sequential recommendation (SR). To investigate the benefits of latent intents and leverage them effectively for recommendation, we propose Intent Contrastive Learning (ICL), a general learning paradigm that leverages a latent intent variable into SR. The core idea is to learn users’ intent distribution functions from unlabeled user behavior sequences and optimize SR models with contrastive self-supervised learning (SSL) by considering the learnt intents to improve recommendation. Specifically, we introduce a latent variable to represent users’ intents and learn the distribution function of the latent variable via clustering. We propose to leverage the learnt intents into SR models via contrastive SSL, which maximizes the agreement between a view of sequence and its corresponding intent. The training is alternated between intent representation learning and the SR model optimization steps within the generalized expectation-maximization (EM) framework. Fusing user intent information into SR also improves model robustness. Experiments conducted on four real-world datasets demonstrate the superiority of the proposed learning paradigm, which improves performance, and robustness against data sparsity and noisy interaction issues 1.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/a4c269e1b7b8ffc0e0c6a9362ea40cc105a53b21

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongzhi Yin
2. Tong Chen
3. Xin Xia
4. Junliang Yu
5. Zi-Liang Huang
6. Jiacheng Li
7. Jingbo Shang
8. Jundong Li

In Information Systems

1. Hongzhi Yin
2. Tong Chen
3. Junliang Yu
4. Xin Xia
5. Jiacheng Li
6. Zi-Liang Huang
7. Jundong Li
8. Jingbo Shang

In Management Science and Operations Research

1. Jiacheng Li
2. Ming Wang
3. Jin Li
4. Jingbo Shang
5. Xin Shen
6. Jinmiao Fu
7. Zi-Liang Huang
8. Jundong Li

Citations in the corpus

• Text Is All You Need: Learning Language Representations for Sequential Recommendation (2023, methodology): “To enrich item features, some approaches [4, 20, 37, 38] incorporate item contexts such as item textual information or categorical features into ID embeddings.”
• Self-Supervised Learning for Recommender Systems: A Survey (2022, background): “ICL [77] has a similar pipeline, but it is designed for sequential recommendation where the semantic prototypes are modeled as user intents and the belonged sequence is a local view of the prototype.”