Wasserstein Collaborative Filtering for Item Cold-start Recommendation

TL;DR

This paper introduces Wasserstein CF, a novel method that leverages Wasserstein distance to improve item cold-start recommendations by effectively modeling content-based similarities and user preferences.

Contribution

It proposes a new Wasserstein distance-based approach for cold-start recommendation that integrates content information with collaborative filtering.

Findings

WCF outperforms state-of-the-art methods in cold-start scenarios.

The approach effectively models content similarity using Wasserstein distance.

Experimental results validate the superiority of WCF over existing methods.

Abstract

The item cold-start problem seriously limits the recommendation performance of Collaborative Filtering (CF) methods when new items have either none or very little interactions. To solve this issue, many modern Internet applications propose to predict a new item's interaction from the possessing contents. However, it is difficult to design and learn a map between the item's interaction history and the corresponding contents. In this paper, we apply the Wasserstein distance to address the item cold-start problem. Given item content information, we can calculate the similarity between the interacted items and cold-start ones, so that a user's preference on cold-start items can be inferred by minimizing the Wasserstein distance between the distributions over these two types of items. We further adopt the idea of CF and propose Wasserstein CF (WCF) to improve the recommendation performance on cold-start items. Experimental results demonstrate the superiority of WCF over state-of-the-art approaches.