Optimal Baseline Corrections for Off-Policy Contextual Bandits

S Gupta, O Jeunen, H Oosterhuis… - Proceedings of the 18th …, 2024 - dl.acm.org
The off-policy learning paradigm allows for recommender systems and general ranking
applications to be framed as decision-making problems, where we aim to learn decision …

Generating TRIZ-inspired guidelines for eco-design using Generative Artificial Intelligence

CKM Lee, J Liang, KL Yung, KL Keung - Advanced Engineering Informatics, 2024 - Elsevier
Environmental considerations are emerging as stimuli for innovation during the eco-design
ideation process. Integrating TRIZ (Teoriya Resheniya Izobretatelskikh Zadatch─ Theory of …

Learning Metrics that Maximise Power for Accelerated A/B-Tests

O Jeunen, A Ustimenko - Proceedings of the 30th ACM SIGKDD …, 2024 - dl.acm.org
Online controlled experiments are a crucial tool to allow for confident decision-making in
technology companies. A North Star metric is defined (such as long-term revenue or user …

Multi-Objective Recommendation via Multivariate Policy Learning

O Jeunen, J Mandav, I Potapov, N Agarwal… - Proceedings of the 18th …, 2024 - dl.acm.org
Real-world recommender systems often need to balance multiple objectives when deciding
which recommendations to present to users. These include behavioural signals (eg clicks …

Personalized Representation from Personalized Generation

S Sundaram, J Chae, Y Tian, S Beery… - ar** Item-wise Rating into Attribute-wise Ratings for Enhanced Personalized Recommendations
P Chaparala, P Nagabhushan… - 2024 15th …, 2024 - ieeexplore.ieee.org
Personalization is the key to any recommendation service, as it relies heavily on analyzing
user interactions with items to uncover patterns and suggest relevant items. While users …

A Graph-Based Approach for Prioritizing Sets of Related Cancer Genes

PJ Ochieng, J Dombi, T Kalmár, Z Maróti, A London… - 2023 - researchsquare.com
Purpose: The identification of cancer-related genes with significant mutations is critical for
deciphering the underlying mechanisms of tumor initiation and progression. Because of the …

Strategies for Accurate Context Retrieval in Retrieval-Augmented Generation Systems Across Diverse Datasets

H Björk, A Andersson - 2024 - diva-portal.org
In recent years, the rapid advancement of generative artificial intelligence has significantly
expanded the horizons of knowledge management and information retrieval. With the …