The negative impact of label noise is well studied in classical supervis...
Generative Adversarial Networks (GANs) have achieved state-of-the-art re...
Tabular data synthesis is an emerging approach to circumvent strict
regu...
Federated Learning (FL) has emerged as a potentially powerful
privacy-pr...
Synthetic tabular data emerges as an alternative for sharing knowledge w...
Federated Learning (FL) is a popular approach for distributed deep learn...
Federated learning is a private-by-design distributed learning paradigm ...
Federated learning allows clients to collaboratively train models on dat...
While data sharing is crucial for knowledge development, privacy concern...
Attacks on Federated Learning (FL) can severely reduce the quality of th...
Deep machine learning models are increasingly deployedin the wild for
pr...
Generative Adversarial Networks (GANs) are increasingly adopted by the
i...
Deep neural networks (DNNs) have become ubiquitous techniques in mobile ...
Generative Adversarial Networks (GANs) are typically trained to synthesi...
Multi-label learning is an emerging extension of the multi-class
classif...
Shapley Value is commonly adopted to measure and incentivize client
part...
Classification algorithms have been widely adopted to detect anomalies f...
While data sharing is crucial for knowledge development, privacy concern...
Sparse Tucker Decomposition (STD) algorithms learn a core tensor and a g...
Labeling real-world datasets is time consuming but indispensable for
sup...
Federated Learning is an emerging distributed collaborative learning par...
Labeling data correctly is an expensive and challenging task in machine
...
DNN learning jobs are common in today's clusters due to the advances in ...
Robustness to label noise is a critical property for weakly-supervised
c...
Today's available datasets in the wild, e.g., from social media and open...
Noisy labeled data is more a norm than a rarity for self-generated conte...
Classification algorithms have been widely adopted to detect anomalies f...
Today's big data clusters based on the MapReduce paradigm are capable of...