Few-shot News Recommendation via Cross-lingual Transfer

TL;DR

This paper introduces a novel unsupervised cross-lingual transfer model for few-shot news recommendation, leveraging shared topics across languages and platforms to improve recommendations with limited user interaction data.

Contribution

It proposes a new cross-lingual transfer approach that aligns news semantics across languages without overlapping users, enhancing few-shot recommendation performance.

Findings

Outperforms baseline methods on real-world datasets

Effectively transfers user preferences across languages

Addresses cold-start in news recommendation systems

Abstract

The cold-start problem has been commonly recognized in recommendation systems and studied by following a general idea to leverage the abundant interaction records of warm users to infer the preference of cold users. However, the performance of these solutions is limited by the amount of records available from warm users to use. Thus, building a recommendation system based on few interaction records from a few users still remains a challenging problem for unpopular or early-stage recommendation platforms. This paper focuses on solving the few-shot recommendation problem for news recommendation based on two observations. First, news at different platforms (even in different languages) may share similar topics. Second, the user preference over these topics is transferable across different platforms. Therefore, we propose to solve the few-shot news recommendation problem by transferring the user-news preference from a many-shot source domain to a few-shot target domain. To bridge two domains that are even in different languages and without any overlapping users and news, we propose a novel unsupervised cross-lingual transfer model as the news encoder that aligns semantically similar news in two domains. A user encoder is constructed on top of the aligned news encoding and transfers the user preference from the source to target domain. Experimental results on two real-world news recommendation datasets show the superior performance of our proposed method on addressing few-shot news recommendation, comparing to the baselines.