Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neural Click Models for Recommender Systems

Mikhail Shirokikh, Ilya Shenbin, Anton Alekseev, Anna Volodkevich, Alexey Vasilev, Andrey V. Savchenko, Sergey Nikolenko

TL;DR

Neural architectures to model the user behavior in recommender systems (RS) inspired by click models for Web search but going beyond standard click models are developed and evaluated.

Abstract

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.

Neural Click Models for Recommender Systems

TL;DR

Neural architectures to model the user behavior in recommender systems (RS) inspired by click models for Web search but going beyond standard click models are developed and evaluated.

Abstract

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.
Paper Structure (5 sections, 3 figures, 1 table)

This paper contains 5 sections, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Datasets and baselines
  3. Models
  4. Experimental Evaluation
  5. Conclusion

Figures (3)

  • Figure 1: Datasets and baselines: (a) ContentWise contentwise; (b) RL4RS rl4rsdataset; (c) logistic regression; (d) Session-wise GRU; (e) Slate-wise GRU; (f) Slate-wise GRU/Transformer; (g) Session-wise Transformer. "Items" are generated with Stable Diffusion Rombach_2022_CVPR.
  • Figure 2: The proposed Random Access NCM (RANCM).
  • Figure 3: The proposed Session-wise Clicked-Only Transformer (SCOT).