no code implementations • 27 Apr 2024 • Mohamed Rashad, Zilong Zhao, Jeremie Decouchant, Lydia Y. Chen
The existing design of training autoencoders in VFL is to train a separate autoencoder in each participant and aggregate the latent representation later.
no code implementations • 12 Mar 2024 • Chaoyi Zhu, Jeroen Galjaard, Pin-Yu Chen, Lydia Y. Chen
As large language models (LLM) are increasingly used for text generation tasks, it is critical to audit their usages, govern their applications, and mitigate their potential harms.
no code implementations • 12 Mar 2024 • Chaoyi Zhu, Jiayi Tang, Hans Brouwer, Juan F. Pérez, Marten van Dijk, Lydia Y. Chen
The backbone technology of tabular synthesizers is rooted in image generative models, ranging from Generative Adversarial Networks (GANs) to recent diffusion models.
2 code implementations • 5 Jan 2024 • Caspar Meijer, Lydia Y. Chen
This survey delves into the application of diffusion models in time-series forecasting.
no code implementations • 3 Nov 2023 • Jui-Yi Tsai, Ya-Wen Teng, Ho Chiok Yew, De-Nian Yang, Lydia Y. Chen
The social graphs synthesized by the generative models are increasingly in demand due to data scarcity and concerns over user privacy.
no code implementations • 12 Sep 2023 • Jeroen M. Galjaard, Robert Birke, Juan Perez, Lydia Y. Chen
We show that the accuracy of Reptile, iMAML, and foMAML drops by up to 42% on the Omniglot and CifarFS datasets when meta-training is affected by label noise.
no code implementations • 3 Feb 2023 • Zilong Zhao, Han Wu, Aad van Moorsel, Lydia Y. Chen
Conditional vector for tabular GANs is a valuable tool to control specific features of generated data.
no code implementations • 17 Nov 2022 • Yujin Zhu, Zilong Zhao, Robert Birke, Lydia Y. Chen
We show that changing the input column order worsens the statistical difference between real and synthetic data by up to 38. 67% due to the encoding of tabular data and the network architectures.
1 code implementation • 12 Oct 2022 • Bart Cox, Lydia Y. Chen, Jérémie Decouchant
Federated Learning (FL) is a popular approach for distributed deep learning that prevents the pooling of large amounts of data in a central server.
no code implementations • 12 Oct 2022 • Zilong Zhao, Robert Birke, Lydia Y. Chen
Mainstream state-of-the-art tabular data synthesizers draw methodologies from Generative Adversarial Networks (GANs), which are composed of a generator and a discriminator.
no code implementations • 28 Apr 2022 • Jin Xu, Chi Hong, Jiyue Huang, Lydia Y. Chen, Jérémie Decouchant
Recent reconstruction attacks apply a gradient inversion optimization on the gradient update of a single minibatch to reconstruct the private data used by clients during training.
no code implementations • 23 Apr 2022 • Federico Lucchetti, Jérémie Decouchant, Maria Fernandes, Lydia Y. Chen, Marcus Völp
Federated learning allows clients to collaboratively train models on datasets that are acquired in different locations and that cannot be exchanged because of their size or regulations.
2 code implementations • 1 Apr 2022 • Zilong Zhao, Aditya Kunar, Robert Birke, Lydia Y. Chen
We extensively evaluate CTAB-GAN+ on data similarity and analysis utility against state-of-the-art tabular GANs.
no code implementations • 7 Feb 2022 • Jiyue Huang, Zilong Zhao, Lydia Y. Chen, Stefanie Roos
Consequently, we design REFD, a defense specifically crafted to protect against data-free attacks.
no code implementations • 31 Jan 2022 • Chi Hong, Jiyue Huang, Lydia Y. Chen
However, they are all based on competing generator-substitute networks and hence encounter training instability. In this paper we propose a data-free model stealing frame-work, MEGA, which is based on collaborative generator-substitute networks and only requires the target model toprovide label prediction for synthetic query examples.
no code implementations • 24 Jan 2022 • Zilong Zhao, Jiyue Huang, Stefanie Roos, Lydia Y. Chen
To mitigate the model degradation, we propose a defense strategy against free-riders in MD-GAN, termed DFG.
no code implementations • 18 Dec 2021 • Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang, Jian Tang, Lydia Y. Chen
The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.
no code implementations • 29 Sep 2021 • Chi Hong, Jiyue Huang, Lydia Y. Chen
Deep machine learning models are increasingly deployed in the wild, subject to adversarial attacks.
1 code implementation • 18 Aug 2021 • Zilong Zhao, Robert Birke, Aditya Kunar, Lydia Y. Chen
And, while learning GANs to synthesize images on FL systems has just been demonstrated, it is unknown if GANs for tabular data can be learned from decentralized data sources.
no code implementations • 4 Aug 2021 • Cosmin Octavian Pene, Amirmasoud Ghiassi, Taraneh Younesian, Robert Birke, Lydia Y. Chen
Multi-label learning is an emerging extension of the multi-class classification where an image contains multiple labels.
no code implementations • 20 Jun 2021 • Jiyue Huang, Chi Hong, Lydia Y. Chen, Stefanie Roos
Shapley Value is commonly adopted to measure and incentivize client participation in federated learning.
1 code implementation • 19 Mar 2021 • Zilong Zhao, Robert Birke, Rui Han, Bogdan Robu, Sara Bouchenak, Sonia Ben Mokhtar, Lydia Y. Chen
Classification algorithms have been widely adopted to detect anomalies for various systems, e. g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i. e., features and labels are correctly set.
1 code implementation • 16 Feb 2021 • Zilong Zhao, Aditya Kunar, Hiek Van der Scheer, Robert Birke, Lydia Y. Chen
In this paper, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types, including a mix of continuous and categorical variables.
no code implementations • 1 Jan 2021 • Amirmasoud Ghiassi, Robert Birke, Lydia Y. Chen
In this paper, we propose to construct a golden symmetric loss (GSL) based on the estimated confusion matrix as to avoid overfitting to noisy labels and learn effectively from hard classes.
no code implementations • 13 Nov 2020 • Taraneh Younesian, Chi Hong, Amirmasoud Ghiassi, Robert Birke, Lydia Y. Chen
Furthermore, relabeling only 10% of the data using the expert's results in over 90% classification accuracy with SVM.
no code implementations • 27 Oct 2020 • Taraneh Younesian, Dick Epema, Lydia Y. Chen
Labeling data correctly is an expensive and challenging task in machine learning, especially for on-line data streams.
no code implementations • 13 Jul 2020 • Amirmasoud Ghiassi, Taraneh Younesian, Robert Birke, Lydia Y. Chen
Based on the insights, we design TrustNet that first adversely learns the pattern of noise corruption, being it both symmetric or asymmetric, from a small set of trusted data.
no code implementations • 10 Jul 2020 • Amirmasoud Ghiassi, Robert Birke, Rui Han, Lydia Y. Chen
Today's available datasets in the wild, e. g., from social media and open platforms, present tremendous opportunities and challenges for deep learning, as there is a significant portion of tagged images, but often with noisy, i. e. erroneous, labels.
no code implementations • 28 Jan 2020 • Taraneh Younesian, Zilong Zhao, Amirmasoud Ghiassi, Robert Birke, Lydia Y. Chen
A central feature of QActor is to dynamically adjust the query limit according to the learning loss for each data batch.
no code implementations • 11 Nov 2019 • Zilong Zhao, Robert Birke, Rui Han, Bogdan Robu, Sara Bouchenak, Sonia Ben Mokhtar, Lydia Y. Chen
Classification algorithms have been widely adopted to detect anomalies for various systems, e. g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i. e., features and labels are correctly set.
no code implementations • 19 Jul 2018 • Chi Hong, Amirmasoud Ghiassi, Yichi Zhou, Robert Birke, Lydia Y. Chen
Our evaluation results on various online scenarios show that BiLA can effectively infer the true labels, with an error rate reduction of at least 10 to 1. 5 percent points for synthetic and real-world datasets, respectively.