Exploration in Sequential Recommender Systems via Graph Representations

Exploration in Sequential Recommender Systems via Graph Representations

Temporal graph networks are powerful tools for solving the cold-start problem in sequential recommender systems. However, graph models are susceptible to feedback loops and data distribution shifts. The paper proposes a simple yet efficient graph-based exploration method for the mitigation of the is...

Full description

Bibliographic Details
Main Authors: Dmitrii Kiselev, Ilya Makarov
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Exploration
fine-tuning
graph neural networks
GNN
graphs
interactive recommender systems
Online Access:https://ieeexplore.ieee.org/document/9963919/

Internet

https://ieeexplore.ieee.org/document/9963919/

Similar Items