CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation

by   Seongwon Jang, et al.

Sequential recommendation techniques provide users with product recommendations fitting their current preferences by handling dynamic user preferences over time. Previous studies have focused on modeling sequential dynamics without much regard to which of the best-selling products (i.e., head items) or niche products (i.e., tail items) should be recommended. We scrutinize the structural reason for why tail items are barely served in the current sequential recommendation model, which consists of an item-embedding layer, a sequence-modeling layer, and a recommendation layer. Well-designed sequence-modeling and recommendation layers are expected to naturally learn suitable item embeddings. However, tail items are likely to fall short of this expectation because the current model structure is not suitable for learning high-quality embeddings with insufficient data. Thus, tail items are rarely recommended. To eliminate this issue, we propose a framework called CITIES, which aims to enhance the quality of the tail-item embeddings by training an embedding-inference function using multiple contextual head items so that the recommendation performance improves for not only the tail items but also for the head items. Moreover, our framework can infer new-item embeddings without an additional learning process. Extensive experiments on two real-world datasets show that applying CITIES to the state-of-the-art methods improves recommendation performance for both tail and head items. We conduct an additional experiment to verify that CITIES can infer suitable new-item embeddings as well.



There are no comments yet.


page 1


ICMT: Item Cluster-Wise Multi-Objective Training for Long-Tail Recommendation

Item recommendation based on historical user-item interactions is of vit...

Embedding models for recommendation under contextual constraints

Embedding models, which learn latent representations of users and items ...

MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation

Recently, self-attention based models have achieved state-of-the-art per...

Long-tail Session-based Recommendation

Session-based recommendation focuses on the prediction of user actions b...

Basket Recommendation with Multi-Intent Translation Graph Neural Network

The problem of basket recommendation (BR) is to recommend a ranking list...

DGEM: A New Dual-modal Graph Embedding Method in Recommendation System

In the current deep learning based recommendation system, the embedding ...

Sliding Spectrum Decomposition for Diversified Recommendation

Content feed, a type of product that recommends a sequence of items for ...

Code Repositories

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.