Graph Collaborative Filtering (GCF) is widely used in personalized recommendation systems. However, GCF suffers from a fundamental problem where features tend to occupy the embedding space inefficiently (by spanning only a low-dimensional subspace).

On User-Generated Content (UGC) platforms, recommendation algorithms significantly impact creators' motivation to produce content as they compete for

As a result, these and other large conferences must rely on automated systems to decide what members of the impaneled reviewer pool will review each paper.

In recommender systems, the collected data used for training is always subject to selection bias, which poses a great challenge for unbiased learning.