Separating and Learning Latent Confounders to Enhancing User Preferences Modeling

arXiv:2311.03381v2 Announce Type: replace-cross
Abstract: Recommender models aim to capture user preferences from historical feedback and then predict user-specific feedback on candidate items. However, the presence of various unmeasured confounders causes deviations between the user preferences in the historical feedback and the true preferences, resulting in models not meeting their expected performance. Existing debias models either (1) specific to solving one particular bias or (2) directly obtain auxiliary information from user historical feedback, which cannot identify whether the learned preferences …

abstract aim arxiv cs.ai cs.ir cs.lg feedback however modeling stat.me true type