A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is
In this paper, we formulate the recommendation models as a causal graph that reflects the cause-effect factors in recommendation, and address the clickbait issue by performing counterfactual inference ... By estimating the click likelihood of a user in the counterfactual world, we are able to reduce the direct effect of exposure features and eliminate the clickbait issue. ... process. • We introduce counterfactual inference into recommendation to mitigate the clickbait issue, and propose a counterfactual recommendation framework which can be applied to any recommender models ...arXiv:2009.09945v3 fatcat:5m3ikhacxfci5ic3g63jatunyu
To address this issue, we introduce 'unit tests' and a mitigation strategy for HI-ADS, as well as a toy environment for modelling real-world issues with HI-ADS in content recommendation, where we demonstrate ... We demonstrate that changes to the learning algorithm, such as the introduction of meta-learning, can cause hidden incentives for auto-induced distributional shift (HI-ADS) to be revealed. ... Thanks to Valentin Dalibard for help with Population Based Training, and Toby Pohlen for help with using Google infrastructure. ...arXiv:2009.09153v1 fatcat:xpduninmzzdrrn5slq3lbr7jfy