Countering Mainstream Bias via End-to-End Adaptive Local Learning

arXiv:2404.08887v1 Announce Type: cross
Abstract: Collaborative filtering (CF) based recommendations suffer from mainstream bias -- where mainstream users are favored over niche users, leading to poor recommendation quality for many long-tail users. In this paper, we identify two root causes of this mainstream bias: (i) discrepancy modeling, whereby CF algorithms focus on modeling mainstream users while neglecting niche users with unique preferences; and (ii) unsynchronized learning, where niche users require more training epochs than mainstream users to reach peak performance. …

arxiv bias cs.ir cs.lg type via