Issue Downloads
A Systematic Study on Reproducibility of Reinforcement Learning in Recommendation Systems
Reproducibility is a main principle in science and fundamental to ensure scientific progress. However, many recent works point out that there are widespread deficiencies for this aspect in the AI field, making the reproducibility of results impractical or ...
Targeted Training for Multi-organization Recommendation
Making recommendations for users in diverse organizations (orgs) is a challenging task for workplace social platforms such as Microsoft Teams and Slack. The current industry-standard model training approaches either use data from all organizations to ...
Intent-Satisfaction Modeling: From Music to Video Streaming
Logged behavioral data is a common resource for enhancing the user experience on streaming platforms. In music streaming, Mehrotra et al. have shown how complementing behavioral data with user intent can help predict and explain user satisfaction. Do ...
On Reducing User Interaction Data for Personalization
Most recommender systems rely on user interaction data for personalization. Usually, the recommendation quality improves with more data. In this work, we study the quality implications when limiting user interaction data for personalization purposes. We ...
Tensor Completion with Provable Consistency and Fairness Guarantees for Recommender Systems
We introduce a new consistency-based approach for defining and solving nonnegative/positive matrix and tensor completion problems. The novelty of the framework is that instead of artificially making the problem well-posed in the form of an application-...