Kyung-Min Kim

Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments

2020 · arXiv (Cornell University)

Graph representation learning is gaining popularity in a wide range of applications, such as social networks analysis, computational biology, and recommender systems. However, different with positive results from many academic studies, applying graph neural networks …

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

2021 · ArXiv.org

In recent years, graph neural networks (GNNs) have been widely adopted in the representation learning of graph-structured data and provided state-of-the-art performance in various applications such as link prediction, node classification, and recommendation. Motivated by …

Scaling Law for Recommendation Models: Towards General-Purpose User Representations

2023 · Proceedings of the AAAI Conference on Artificial Intelligence

Recent advancement of large-scale pretrained models such as BERT, GPT-3, CLIP, and Gopher, has shown astonishing achievements across various task domains. Unlike vision recognition and language models, studies on general-purpose user representation at scale still …