# Sequential Recommendation for Cold-start Users with Meta Transitional Learning

arXiv: https://arxiv.org/abs/2107.06427 · HTML: https://mlsanity.com/paper/2107.06427/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2021.

## Built on by (most cited first, 7 of 7)

- [User-Centric Conversational Recommendation with Multi-Aspect User Modeling](https://mlsanity.com/paper/2204.09263/) (2022)
- [Comprehensive Fair Meta-learned Recommender System](https://mlsanity.com/paper/2206.04789/) (2022)
- [ELECRec: Training Sequential Recommenders as Discriminators](https://mlsanity.com/paper/2204.02011/) (2022)
- [IDNP: Interest Dynamics Modeling using Generative Neural Processes for Sequential Recommendation](https://mlsanity.com/paper/2208.04600/) (2022)
- [Leaping Through Time with Gradient-based Adaptation for Recommendation](https://mlsanity.com/paper/2112.05914/) (2021)
- [ClusterSeq: Enhancing Sequential Recommender Systems with Clustering based Meta-Learning](https://mlsanity.com/paper/2307.13766/) (2023)
- [When to Switch, Not Just What: Transition Quality Prediction in Clash Royale](https://mlsanity.com/paper/2605.21868/) (2026)

## Abstract (arXiv)

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.