Noseong Park

Two Problems in Knowledge Graph Embedding: Non-Exclusive Relation Categories and Zero Gradients

2019

Knowledge graph embedding (KGE) learns latent vector representations of named entities (i.e., vertices) and relations (i.e., edge labels) of knowledge graphs. Herein, we address two problems in KGE. First, relations may belong to one or …

Linear, or Non-Linear, That is the Question!

2021 · arXiv (Cornell University)

There were fierce debates on whether the non-linear embedding propagation of GCNs is appropriate to GCN-based recommender systems. It was recently found that the linear embedding propagation shows better accuracy than the non-linear embedding propagation. …

MadSGM: Multivariate Anomaly Detection with Score-based Generative Models

2023 · arXiv (Cornell University)

The time-series anomaly detection is one of the most fundamental tasks for time-series. Unlike the time-series forecasting and classification, the time-series anomaly detection typically requires unsupervised (or self-supervised) training since collecting and labeling anomalous observations …