Debiased Model-based Interactive Recommendation

arXiv:2402.15819v1 Announce Type: cross
Abstract: Existing model-based interactive recommendation systems are trained by querying a world model to capture the user preference, but learning the world model from historical logged data will easily suffer from bias issues such as popularity bias and sampling bias. This is why some debiased methods have been proposed recently. However, two essential drawbacks still remain: 1) ignoring the dynamics of the time-varying popularity results in a false reweighting of items. 2) taking the unknown samples …

abstract arxiv bias cs.ir cs.lg data interactive recommendation recommendation systems sampling systems type will world