Recommendation unlearning is an emerging task to erase the influences of user-specified
data from a trained recommendation model. Most existing research follows the paradigm of …

In recent years, deep learning on graphs has achieved remarkable success in various
domains. However, the reliance on annotated graph data remains a significant bottleneck …

Recovering user preferences from user-item interaction matrices is a key challenge in
recommender systems. While diffusion models can sample and reconstruct preferences from …

Recommendation systems are vital for personalized experiences in today's digital
landscape. This study thoroughly examines collaborative filtering (CF) algorithms and their …

Abstract Multi-Agent Systems (MAS) have become integral in various applications,
necessitating effective communication and coordination among agents. This research …

Large-scale signal processing often faces challenges due to the diversity and volume of
data generated from various sources. Traditional methods may struggle to effectively …

Abstract Collaborative Signal Augmentation presents unique challenges that necessitate
advanced solutions to improve performance. Traditional signal processing methods often …