no code implementations • 9 Oct 2020 • Keondo Park, Wonyoung Jang, Woochul Lee, Kisung Nam, Kihong Seong, Kyuwook Chai, Wen-Syan Li
After the COVID-19 outbreak, it has become important to automatically detect whether people are wearing masks in order to reduce risk of front-line workers.
no code implementations • 5 Aug 2022 • Tien-Cuong Bui, Wen-Syan Li, Sang-Kyun Cha
To address these challenges, we propose a multi-level GNN explanation framework based on an observation that GNN is a multimodal learning process of multiple components in graph data.
no code implementations • 20 Oct 2022 • Tien-Cuong Bui, Van-Duc Le, Wen-Syan Li, Sang Kyun Cha
Therefore, we propose a novel GNN explanation framework named SCALE, which is general and fast for explaining predictions.
no code implementations • 3 Nov 2022 • Tien-Cuong Bui, Van-Duc Le, Wen-Syan Li, Sang Kyun Cha
Graph Neural Networks (GNNs) are widely used in many modern applications, necessitating explanations for their decisions.
no code implementations • 25 Apr 2023 • Van-Duc Le, Cuong-Tien Bui, Wen-Syan Li
Another critical issue is the model accuracy degradation by the difference between training data and testing data during the ML lifetime, which leads to lifecycle rebuild.