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

TL;DR

This paper introduces CVAR, a model-agnostic framework that improves item cold-start recommendations by generating enhanced embeddings using a conditional variational autoencoder, leveraging historical and emerging interaction data without extra data requirements.

Contribution

The paper proposes a novel CVAR framework that effectively addresses item cold-start issues in recommendation systems without additional data, compatible with various models, and utilizing both historical and recent interactions.

Findings

CVAR outperforms baseline methods in offline experiments.

CVAR demonstrates robustness and effectiveness in online A/B tests.

The approach is compatible with different recommendation backbones.

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.