1 code implementation • 10 Jan 2024 • Anna Stephens, Francisco Santos, Pang-Ning Tan, Abdol-Hossein Esfahanian
Graph neural networks (GNN) are a powerful tool for combining imaging and non-imaging medical information for node classification tasks.
1 code implementation • 5 May 2022 • Asadullah Hill Galib, Andrew McDonald, Tyler Wilson, Lifeng Luo, Pang-Ning Tan
Accurate forecasting of extreme values in time series is critical due to the significant impact of extreme events on human and natural systems.
1 code implementation • 2 May 2022 • Andrew McDonald, Pang-Ning Tan, Lifeng Luo
In particular, existing normalizing flow architectures struggle to model multivariate extremes, characterized by heavy-tailed marginal distributions and asymmetric tail dependence among variables.
no code implementations • 29 Sep 2021 • Boyang Liu, Zhuangdi Zhu, Pang-Ning Tan, Jiayu Zhou
We first discuss the limitations of directly using the noisy-label defense algorithms to defend against backdoor attacks.
no code implementations • 12 Feb 2021 • Boyang Liu, Mengying Sun, Ding Wang, Pang-Ning Tan, Jiayu Zhou
Training deep neural models in the presence of corrupted supervision is challenging as the corrupted data points may significantly impact the generalization performance.
2 code implementations • 1 Jan 2021 • Boyang Liu, Ding Wang, Kaixiang Lin, Pang-Ning Tan, Jiayu Zhou
Unsupervised anomaly detection plays a crucial role in many critical applications.
no code implementations • 1 Jan 2021 • Boyang Liu, Mengying Sun, Ding Wang, Pang-Ning Tan, Jiayu Zhou
Training deep neural models in the presence of corrupted supervisions is challenging as the corrupted data points may significantly impact the generalization performance.
no code implementations • 7 Oct 2020 • Farzan Masrour, Pang-Ning Tan, Abdol-Hossein Esfahanian
We show how the function can be extended to a group fairness metric known as fairness visibility and demonstrate its relationship to demographic parity.
no code implementations • 21 May 2019 • Shuai Yuan, Pang-Ning Tan, Kendra Spence Cheruvelil, Sarah M. Collins, Patricia A. Soranno
To address these two challenges, first, we develop a spatially constrained spectral clustering framework for region delineation that incorporates the tradeoff between region homogeneity and spatial contiguity.
no code implementations • IEEE 2018 • Tyler Wilson, Pang-Ning Tan, Lifeng Luo
Specifically, our proposed approach uses an LSTM to capture the inherent temporal autocorrelation of the data and a graph convolution to model its spatial relationships.