Sequential Recommendation for Cold-start Users with Meta Transitional Learning

TL;DR

This paper introduces MetaTL, a meta-learning framework designed to improve sequential recommendations for cold-start users by effectively modeling their transition patterns with limited interactions.

Contribution

MetaTL formulates cold-start sequential recommendation as a few-shot learning problem and employs meta-learning to enable rapid adaptation to new users.

Findings

MetaTL outperforms existing models on cold-start recommendation tasks.

The framework effectively captures user transition patterns with minimal data.

MetaTL demonstrates fast learning capabilities for new users.

Abstract

A fundamental challenge for sequential recommenders is to capture the sequential patterns of users toward modeling how users transit among items. In many practical scenarios, however, there are a great number of cold-start users with only minimal logged interactions. As a result, existing sequential recommendation models will lose their predictive power due to the difficulties in learning sequential patterns over users with only limited interactions. In this work, we aim to improve sequential recommendation for cold-start users with a novel framework named MetaTL, which learns to model the transition patterns of users through meta-learning. Specifically, the proposed MetaTL: (i) formulates sequential recommendation for cold-start users as a few-shot learning problem; (ii) extracts the dynamic transition patterns among users with a translation-based architecture; and (iii) adopts meta transitional learning to enable fast learning for cold-start users with only limited interactions, leading to accurate inference of sequential interactions.