Search Results for author: Namyong Park

Found 12 papers, 3 papers with code

Forward Learning of Graph Neural Networks

no code implementations16 Mar 2024 Namyong Park, Xing Wang, Antoine Simoulin, Shuai Yang, Grey Yang, Ryan Rossi, Puja Trivedi, Nesreen Ahmed

To address these limitations, the forward-forward algorithm (FF) was recently proposed as an alternative to BP in the image classification domain, which trains NNs by performing two forward passes over positive and negative data.

Drug Discovery Graph Learning +2

MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning

1 code implementation18 Jun 2022 Namyong Park, Ryan Rossi, Nesreen Ahmed, Christos Faloutsos

In this work, we develop the first meta-learning approach for evaluation-free graph learning model selection, called MetaGL, which utilizes the prior performances of existing methods on various benchmark graph datasets to automatically select an effective model for the new graph, without any model training or evaluations.

BIG-bench Machine Learning Graph Learning +3

CGC: Contrastive Graph Clustering for Community Detection and Tracking

1 code implementation5 Apr 2022 Namyong Park, Ryan Rossi, Eunyee Koh, Iftikhar Ahamath Burhanuddin, Sungchul Kim, Fan Du, Nesreen Ahmed, Christos Faloutsos

Especially, deep graph clustering (DGC) methods have successfully extended deep clustering to graph-structured data by learning node representations and cluster assignments in a joint optimization framework.

Clustering Community Detection +4

Knowledge-Guided Dynamic Systems Modeling: A Case Study on Modeling River Water Quality

no code implementations1 Mar 2021 Namyong Park, MinHyeok Kim, Nguyen Xuan Hoai, R. I., McKay, Dong-Kyun Kim

Modeling real-world phenomena is a focus of many science and engineering efforts, such as ecological modeling and financial forecasting, to name a few.

TAG

J-Recs: Principled and Scalable Recommendation Justification

no code implementations11 Nov 2020 Namyong Park, Andrey Kan, Christos Faloutsos, Xin Luna Dong

Online recommendation is an essential functionality across a variety of services, including e-commerce and video streaming, where items to buy, watch, or read are suggested to users.

Persuasiveness

MultiImport: Inferring Node Importance in a Knowledge Graph from Multiple Input Signals

no code implementations22 Jun 2020 Namyong Park, Andrey Kan, Xin Luna Dong, Tong Zhao, Christos Faloutsos

MultiImport is a latent variable model that captures the relation between node importance and input signals, and effectively learns from multiple signals with potential conflicts.

Dropout Prediction over Weeks in MOOCs by Learning Representations of Clicks and Videos

no code implementations5 Feb 2020 Byungsoo Jeon, Namyong Park

This paper addresses a key challenge in MOOC dropout prediction, namely to build meaningful representations from clickstream data.

Cannot find the paper you are looking for? You can Submit a new open access paper.