Publications
2022
Hop-Count Based Self-Supervised Anomaly Detection on Attributed Networks.
Tianjin Huang, Yulong Pei, Vlado Menkovski,Mykola Pechenizkiy. ECML 2022.
PDFSuperposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training.
Lu Yin, Vlado Menkovski, Meng Fang, Tianjin Huang ,Yulong Pei ,Mykola Pechenizkiy，Decebal Constantin Mocanu，Shiwei Liu. UAI 2022.
PDF
2021
ResGCN: attention-based deep residual modeling for anomaly detection on attributed networks.
Yulong Pei, Tianjin Huang, Werner van Ipenburg, Mykola Pechenizkiy. Journal:Machine Learning 111, 519–541 .
PDFOn Generalization of Graph Autoencoders with Adversarial Training.
Tianjin Huang, Yulong Pei, Vlado Menkovski,Mykola Pechenizkiy. ECML 2021.
PDFCalibrated Adversarial Training.
Tianjin Huang, Vlado Menkovski, Yulong Pei, Mykola Pechenizkiy. ACML 2021.
PDFDirection-aggregated attack for transferable adversarial examples.
Tianjin Huang, Vlado Menkovski, Yulong Pei, Yuhao Wang, Mykola Pechenizkiy. Journal: ACM JETC 18(3),1-22 .
PDF
2020
- Bridging the performance gap between fgsm and pgd adversarial training.
Tianjin Huang, Vlado Menkovski, Yulong Pei, Mykola Pechenizkiy. In Arxiv .
PDF
2017
A new method to estimate changes in glacier surface elevation based on polynomial fitting of sparse ICESat—GLAS footprints.
Tianjin Huang, Li Jia, Massimo Menenti, Jing Lu, Jie Zhou, Guangcheng Hu. Journal: Sensors 17(8),1803 .
PDF青藏高原地区湖泊面积插补迭代自动提取.
黄田进， 梁丁丁， 贾立， 张静潇， 卢静， 周杰. 遥感技术与应用 32(2),289-298 .
PDF