3

Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition
Deep Neural Networks (DNNs) have achieved remarkable success in addressing many previously unsolvable tasks. However, the storage and …
Xitong Zhang, Ismail R Alkhouri, Rongrong Wang
Unlocking Tuning-free Generalization: Minimizing the PAC-Bayes Bound with Trainable Priors
Our proposed tuning-free PAC-Bayes training framework achieves test performance comparable to that of SGD/Adam, even when the latter are optimized through a complete grid search and supplemented with additional regularization terms.
Xitong Zhang, Avrajit Ghosh, Guangliang Liu, Rongrong Wang
PDF Cite
Unlocking Tuning-free Generalization: Minimizing the PAC-Bayes Bound with Trainable Priors
Can Directed Graph Neural Networks be Adversarially Robust?
The existing research on robust Graph Neural Networks (GNNs) fails to acknowledge the significance of directed graphs in providing rich …
Zhichao Hou, Xitong Zhang, Wei Wang, Charu C. Aggarwal, Xiaorui Liu
PDF Cite
Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks
Monitoring changes inside a reservoir in real time is crucial for the success of CO2 injection and long-term storage. Machine learning …
Yanhua Liu, Xitong Zhang, Ilya Tsvankin, Youzuo Lin
PDF Cite
Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks
PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs
Networks are ubiquitous in many real-world applications (e.g., social networks encoding trust/distrust relationships, correlation …
Yixuan He, Xitong Zhang, Junjie Huang, Benedek Rozemberczki, Mihai Cucuringu, Gesine Reinert
PDF Cite Code Project
PyTorch Geometric Signed Directed: A Software Package on Graph Neural Networks for Signed and Directed Graphs