analiza aiqbench
This research introduces Probabilistic Residual Learning (PRL), a causal Bayesian framework designed to refine existing deep learning recommender systems by modeling residuals between base predictions and ground truth. By probabilistically grouping users and accounting for domain-level confounders via do-calculus, the method offers a plug-and-play approach that improves recommendation accuracy while uncovering meaningful user clusters without requiring model retraining from scratch.
Probabilistic Residual Learning for Online Recommendations
arXiv:2607.20863v1 Announce Type: cross Abstract: Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffer from the black-box nature and computational complexity of the underlying models, making it difficult to systematically enhance their recommendation capabilities. To address this problem, we propose Probabilistic Residual Learning (PRL), a causal Bayesian recommendation model that models the residual between ground-truth and base predictions, enabling targeted refinement of existing systems. Specifically, PRL (1) probabilistically groups users for localized residual modeling, (2) models domain-level confounders that influence user and item representations, and (3) aggregates cluster-specific residual predictions over the confounders using do-calculus. Experiments demonstrate that our plug-and-play PRL is compatible with various base deep learning recommender systems, improving their performance while automatically discovering meaningful user clusters.
Abstract:Modern recommender systems are typically based on deep learning (DL) models, where a dense encoder learns representations of users and items. As a result, these systems often suffer from the black-box nature and computational complexity of the underlying models, making it difficult to systematically enhance their recommendation capabilities. To address this problem, we propose Probabilistic Residual Learning (PRL), a causal Bayesian recommendation model that models the residual between ground-truth and base predictions, enabling targeted refinement of existing systems. Specifically, PRL (1) probabilistically groups users for localized residual modeling, (2) models domain-level confounders that influence user and item representations, and (3) aggregates cluster-specific residual predictions over the confounders using do-calculus. Experiments demonstrate that our plug-and-play PRL is compatible with various base deep learning recommender systems, improving their performance while automatically discovering meaningful user clusters.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2607.20863 [cs.IR]
(or arXiv:2607.20863v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2607.20863 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 157 cuvinte
Subiecte conexe
Report the Floor: A Training-Free Conformal Interval Is a Mandatory Baseline for Probabilistic Time-Series Forecasting
arXiv · 9 iun. 2026
K-VARK: Kernelized Variance-Aware Residual Kalman Filter for Sensorless Force Estimation in Collaborative Robots
arXiv · 17 iun. 2026
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
RQ-Reg: A Residual-Quantization-Based Framework for Continuous Value Prediction in Recommender Systems
arXiv · 26 sept. 2026