Sequential Recommendation for Cold-start Users with Meta Transitional Learning
This addresses the challenge of making accurate sequential recommendations for cold-start users in practical scenarios, representing an incremental improvement over existing methods.
The paper tackles the problem of sequential recommendation for cold-start users with minimal interactions by proposing MetaTL, a meta-learning framework that models user transition patterns, resulting in improved predictive accuracy for these users.
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.