End-to-end Learnable Diversity-aware News Recommendation

Understand

Diversity is an important factor in providing high-quality personalized news recommendations.

• However, most existing news recommendation methods only aim to optimize recommendation accuracy while ignoring diversity.
• Reranking is a widely used post-processing technique to promote the diversity of top recommendation results.
• However, the recommendation model is not perfect and errors may be propagated and amplified in a cascaded recommendation algorithm.