Cross-Dataset Propensity Estimation for Debiasing Recommender Systems
This work addresses distribution shift issues in recommender systems for improved recommendation accuracy, though it appears incremental as it builds on existing causal inference methods.
The paper tackled the problem of selection bias in recommender system datasets by using two differently quantized datasets to mitigate distribution shift, resulting in significant performance improvements over single-dataset methods and other combination approaches.
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.