Cross-Dataset Propensity Estimation for Debiasing Recommender SystemsDownload PDF

Published: 21 Oct 2022, Last Modified: 05 May 2023NeurIPS 2022 Workshop DistShift PosterReaders: Everyone
Abstract: Datasets for training recommender systems are often subject to distribution shift induced by users' and recommenders' selection biases. In this paper, we study the impact of selection bias on datasets with different quantization. We then leverage two differently quantized datasets from different source distributions to mitigate distribution shift by applying the inverse probability scoring method from causal inference. Empirically, our approach gains significant performance improvement over single-dataset methods and alternative ways of combining two datasets.
1 Reply