In the Eye of the Beholder: Robust Prediction with Causal User ModelingDownload PDF

Published: 31 Oct 2022, Last Modified: 11 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: Behavioral User Modeling, Bounded Rationality, Robust Prediction, Causal Representation Learning
TL;DR: We propose a learning framework for relevance prediction that is robust to distributional changes by accounting for users' causal perceptions.
Abstract: Accurately predicting the relevance of items to users is crucial to the success of many social platforms. Conventional approaches train models on logged historical data; but recommendation systems, media services, and online marketplaces all exhibit a constant influx of new content---making relevancy a moving target, to which standard predictive models are not robust. In this paper, we propose a learning framework for relevance prediction that is robust to changes in the data distribution. Our key observation is that robustness can be obtained by accounting for \emph{how users causally perceive the environment}. We model users as boundedly-rational decision makers whose causal beliefs are encoded by a causal graph, and show how minimal information regarding the graph can be used to contend with distributional changes. Experiments in multiple settings demonstrate the effectiveness of our approach.
Supplementary Material: pdf
14 Replies

Loading