Learning to Recommend via Meta Parameter Partition

Abstract

In this paper we propose to solve an important problem in recommendation -- user cold start, based on meta leaning method. Previous meta learning approaches finetune all parameters for each new user, which is both computing and storage expensive. In contrast, we divide model parameters into fixed and adaptive parts and develop a two-stage meta learning algorithm to learn them separately. The fixed part, capturing user invariant features, is shared by all users and is learned during offline meta learning stage. The adaptive part, capturing user specific features, is learned during online meta learning stage. By decoupling user invariant parameters from user dependent parameters, the proposed approach is more efficient and storage cheaper than previous methods. It also has potential to deal with catastrophic forgetting while continually adapting for streaming coming users. Experiments on production data demonstrates that the proposed method converges faster and to a better performance than baseline methods. Meta-training without online meta model finetuning increases the AUC from 72.24% to 74.72% (2.48% absolute improvement). Online meta training achieves a further gain of 2.46\% absolute improvement comparing with offline meta training.

References in corpus (13)

• Overcoming catastrophic forgetting in neural networks
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• On First-Order Meta-Learning Algorithms
• Deep Reinforcement Learning for Page-wise Recommendations
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Wide & Deep Learning for Recommender Systems
• Sequential Click Prediction for Sponsored Search with Recurrent Neural Networks
• Deep Reinforcement Learning for List-wise Recommendations
• Online Meta-Learning
• Generative Adversarial User Model for Reinforcement Learning Based Recommendation System
• Gradient based sample selection for online continual learning
• Product-based Neural Networks for User Response Prediction

Cited by in corpus (2)

• MAMO: Memory-Augmented Meta-Optimization for Cold-start Recommendation
• Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systems