Leveraging attribute latent features for addressing new item cold-start issue

Article Computer Science, Artificial Intelligence

Attribute Graph Neural Networks for Strict Cold Start Recommendation

Tieyun Qian et al.

Summary: Rating prediction is a classic problem addressed by matrix factorization, but recent advancements in deep learning, particularly graph neural networks, have shown impressive progress. This study introduces a new AGNN framework that utilizes attribute graphs to learn preference embeddings for strict cold start users/items.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

An optimized item-based collaborative filtering algorithm

Chigozirim Ajaegbu

Summary: Collaborative filtering has been an emerging alternative recommender system, but researchers have raised doubts about its effectiveness in handling ratings with limited number of users or no rating record from users. This study proposed an algorithm to balance the traditional measurement metrics and showed that it offered a better item-based collaborative filtering algorithm than the existing one, especially in cold-start situations. Additionally, the proposed algorithm complemented the strength of the three traditional measurement metrics and retained the good features of the existing item-based collaborative filtering algorithm.

JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence