Unifying Online and Counterfactual Learning to Rank
This work aims to bridge the gap between online and counterfactual learning to rank methods, which is a significant problem for researchers and practitioners in information retrieval and recommender systems.
This paper addresses the problem of optimizing ranking systems using user interactions, which are typically handled by either online or counterfactual learning methods. The authors propose a novel intervention-aware estimator that effectively operates in both online and counterfactual scenarios, demonstrating that it can greatly benefit from online interventions, unlike existing counterfactual methods.
Optimizing ranking systems based on user interactions is a well-studied problem. State-of-the-art methods for optimizing ranking systems based on user interactions are divided into online approaches - that learn by directly interacting with users - and counterfactual approaches - that learn from historical interactions. Existing online methods are hindered without online interventions and thus should not be applied counterfactually. Conversely, counterfactual methods cannot directly benefit from online interventions. We propose a novel intervention-aware estimator for both counterfactual and online Learning to Rank (LTR). With the introduction of the intervention-aware estimator, we aim to bridge the online/counterfactual LTR division as it is shown to be highly effective in both online and counterfactual scenarios. The estimator corrects for the effect of position bias, trust bias, and item-selection bias by using corrections based on the behavior of the logging policy and on online interventions: changes to the logging policy made during the gathering of click data. Our experimental results, conducted in a semi-synthetic experimental setup, show that, unlike existing counterfactual LTR methods, the intervention-aware estimator can greatly benefit from online interventions.