TY - GEN

T1 - Neural Click Models for Recommender Systems

AU - Shirokikh, Mikhail

AU - Shenbin, Ilya

AU - Alekseev, Anton

AU - Volodkevich, Anna

AU - Vasilev, Alexey

AU - Savchenko, Andrey V

AU - Nikolenko, Sergey

N1 - Conference code: 47

PY - 2024/7/10

Y1 - 2024/7/10

N2 - We develop and evaluate neural architectures to model the user behavior in recommender systems (RS) inspired by click models for Web search but going beyond standard click models. Proposed architectures include recurrent networks, Transformer-based models that alleviate the quadratic complexity of self-attention, adversarial and hierarchical architectures. Our models outperform baselines on the ContentWise and RL4RS datasets and can be used in RS simulators to model user response for RS evaluation and pretraining.

AB - We develop and evaluate neural architectures to model the user behavior in recommender systems (RS) inspired by click models for Web search but going beyond standard click models. Proposed architectures include recurrent networks, Transformer-based models that alleviate the quadratic complexity of self-attention, adversarial and hierarchical architectures. Our models outperform baselines on the ContentWise and RL4RS datasets and can be used in RS simulators to model user response for RS evaluation and pretraining.

KW - adversarial learning

KW - recommender systems

KW - user response function

UR - https://www.mendeley.com/catalogue/6caded53-13e0-351b-94d1-2e2bb6444182/

U2 - 10.1145/3626772.3657939

DO - 10.1145/3626772.3657939

M3 - Conference contribution

SN - 9798400704314

SP - 2553

EP - 2558

BT - SIGIR 2024 - Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval

T2 - 47th International ACM SIGIR Conference on Research and Development in Information Retrieva

Y2 - 14 July 2024 through 18 July 2024

ER -