David Liu

Identifying and Upweighting Power-Niche Users to Mitigate Popularity Bias in Recommendations Recommender systems have been shown to exhibit popularity bias by over-recommending popular items and under-recommending relevant niche items. We seek to understand niche users in benchmark recommenda...

📄 Paper links:

• When Collaborative Filtering is not Collaborative: Unfairness of PCA for Recommendations (FAccT ’25)
arxiv.org/abs/2310.09687

• Identifying and Upweighting Power-Niche Users to Mitigate Popularity Bias in Recommendations (WWW ’26)
arxiv.org/abs/2509.17265

In the episode, I discuss:

• 📉 How PCA embeddings can misrepresent minority preferences

• ⚡ Who power-niche users are and why they matter

• 🔬 Open research questions on aligning group preferences in AI models

Fairness in PCA-Based Recommenders

🎙️ I had a great time joining the Data Skeptic podcast to talk about my work on recommender systems

If you're interested in embeddings, aligning group preferences, or music recommendations, check out the episode below 👇

open.spotify.com/episode/6IsP...