Open-source research

MetaSR

The official implementation of a meta-learning framework that bridges next-item prediction and masked-language modeling for recommendation.

Year
2026
Status
active
Focus
Python · Meta-Learning · Sequential Recommendation

What it does

MetaSR connects two common training paradigms for sequential recommendation: next-item prediction and masked-language modeling. Its meta-learning formulation is designed to transfer useful structure between the two objectives.

The public repository provides the official implementation and experiment setup for the ACM TKDD paper, including the model and data-processing workflow.

Evidence and scope

This page is a concise guide to the work. Use the primary paper for the experimental setup, quantitative results, limitations, and formal claims; use the repository for the implementation and current reproduction instructions.