3 papers
cs.IR2024
Polyhedral Conic Classifier for CTR Prediction
Beyza Turkmen, Ramazan Tarik Turksoy, Hasan Saribas +1
This paper introduces a novel approach for click-through rate (CTR) prediction within industrial recommender systems, addressing the inherent challenges of numerical imbalance and…
cs.IR2024
Pairwise Ranking Loss for Multi-Task Learning in Recommender Systems
Furkan Durmus, Hasan Saribas, Said Aldemir +2
Multi-Task Learning (MTL) plays a crucial role in real-world advertising applications such as recommender systems, aiming to achieve robust representations while minimizing resourc…
cs.LG2023
Degree-based stratification of nodes in Graph Neural Networks
Ameen Ali, Hakan Cevikalp, Lior Wolf
Despite much research, Graph Neural Networks (GNNs) still do not display the favorable scaling properties of other deep neural networks such as Convolutional Neural Networks and Tr…