Sequential Scenario-Specific Meta Learner for Online Recommendation

Abstract

Cold-start problems are long-standing challenges for practical recommendations. Most existing recommendation algorithms rely on extensive observed data and are brittle to recommendation scenarios with few interactions. This paper addresses such problems using few-shot learning and meta learning. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. To accomplish this, we combine the scenario-specific learning with a model-agnostic sequential meta-learning and unify them into an integrated end-to-end framework, namely Scenario-specific Sequential Meta learner (or s^2 meta). By doing so, our meta-learner produces a generic initial model through aggregating contextual information from a variety of prediction tasks while effectively adapting to specific tasks by leveraging learning-to-learn knowledge. Extensive experiments on various real-world datasets demonstrate that our proposed model can achieve significant gains over the state-of-the-arts for cold-start problems in online recommendation. Deployment is at the Guess You Like session, the front page of the Mobile Taobao.

Accepted to KDD 2019

References in corpus (7)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Inductive Representation Learning on Large Graphs
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Recurrent Neural Networks with Top-k Gains for Session-based Recommendations
• On First-Order Meta-Learning Algorithms
• Wide & Deep Learning for Recommender Systems

Cited by in corpus (2)

• Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
• MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation