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

by   Xu Zhao, et al.

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.


page 1

page 2

page 3

page 4


Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up

The gap between the randomly initialized item ID embedding and the well-...

CoMeta: Enhancing Meta Embeddings with Collaborative Information in Cold-start Problem of Recommendation

The cold-start problem is quite challenging for existing recommendation ...

Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks

Recently, embedding techniques have achieved impressive success in recom...

Better Generalization with Semantic IDs: A case study in Ranking for Recommendations

Training good representations for items is critical in recommender model...

GIFT: Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction

Short video has witnessed rapid growth in China and shows a promising ma...

Mutually-Regularized Dual Collaborative Variational Auto-encoder for Recommendation Systems

Recently, user-oriented auto-encoders (UAEs) have been widely used in re...

A Bayesian Approach to Conversational Recommendation Systems

We present a conversational recommendation system based on a Bayesian ap...

Please sign up or login with your details

Forgot password? Click here to reset