Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder

Abstract

Embedding & MLP has become a paradigm for modern large-scale recommendation system. However, this paradigm suffers from the cold-start problem which will seriously compromise the ecological health of recommendation systems. This paper attempts to tackle the item cold-start problem by generating enhanced warmed-up ID embeddings for cold items with historical data and limited interaction records. From the aspect of industrial practice, we mainly focus on the following three points of item cold-start: 1) How to conduct cold-start without additional data requirements and make strategy easy to be deployed in online recommendation scenarios. 2) How to leverage both historical records and constantly emerging interaction data of new items. 3) How to model the relationship between item ID and side information stably from interaction data. To address these problems, we propose a model-agnostic Conditional Variational Autoencoder based Recommendation(CVAR) framework with some advantages including compatibility on various backbones, no extra requirements for data, utilization of both historical data and recent emerging interactions. CVAR uses latent variables to learn a distribution over item side information and generates desirable item ID embeddings using a conditional decoder. The proposed method is evaluated by extensive offline experiments on public datasets and online A/B tests on Tencent News recommendation platform, which further illustrate the advantages and robustness of CVAR.

arXiv comment6 pages, 2 figures, accepted as SIGIR 2022 short paper

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Sentences and Documents
• CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network
• DisenHAN: Disentangled Heterogeneous Graph Attention Network for Recommendation
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• ESAM: Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation
• Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction
• Quantitative analysis of Matthew effect and sparsity problem of recommender systems
• Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings
• Contrastive Learning for Cold-Start Recommendation

Cited by in corpus (4)

• Contrastive Collaborative Filtering for Cold-Start Item Recommendation
• VM-Rec: A Variational Mapping Approach for Cold-start User Recommendation
• The Limits of Graph Samplers for Training Inductive Recommender Systems: Extended results
• Harnessing Light for Cold-Start Recommendations: Leveraging Epistemic Uncertainty to Enhance Performance in User-Item Interactions