document

Defending Against Free-Riders Attacks in Distributed Generative Adversarial Networks

Zhao, Z. (author), Huang, J. (author), Chen, Lydia Y. (author), Roos, S. (author)

Generative Adversarial Networks (GANs) are increasingly adopted by the industry to synthesize realistic images using competing generator and discriminator neural networks. Due to data not being centrally available, Multi-Discriminator (MD)-GANs training frameworks employ multiple discriminators that have direct access to the real data....

conference paper 2024

document

FedViT: Federated continual learning of vision transformer at edge

Zuo, Xiaojiang (author), Luopan, Yaxin (author), Han, Rui (author), Zhang, Qinglong (author), Liu, Chi Harold (author), Wang, Guoren (author), Chen, Lydia Y. (author)

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral part of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge...

journal article 2024

document

ElasticDNN: On-Device Neural Network Remodeling for Adapting Evolving Vision Domains at Edge

Zhang, Qinglong (author), Han, Rui (author), Liu, Chi Harold (author), Wang, Guoren (author), Chen, Lydia Y. (author)

Executing deep neural networks (DNN) based vision tasks on edge devices encounters challenging scenarios of significant and continually evolving data domains (e.g. background or subpopulation shift). With limited resources, the state-of-the-art domain adaptation (DA) methods either cause high training overheads on large DNN models, or incur...

journal article 2024

document

Robust Learning via Golden Symmetric Loss of (un)Trusted Labels

Ghiassi, S. (author), Birke, Robert (author), Chen, Lydia Y. (author)

Learning robust deep models against noisy labels becomes ever critical when today's data is commonly collected from open platforms and subject to adversarial corruption. The information on the label corruption process, i.e., corruption matrix, can greatly enhance the robustness of deep models but still fall behind in combating hard classes....

conference paper 2023

document

Fabricated Flips: Poisoning Federated Learning without Data

Huang, J. (author), Zhao, Z. (author), Chen, Lydia Y. (author), Roos, S. (author)

Attacks on Federated Learning (FL) can severely reduce the quality of the generated models and limit the usefulness of this emerging learning paradigm that enables on-premise decentralized learning. However, existing untargeted attacks are not practical for many scenarios as they assume that i) the attacker knows every update of benign...

conference paper 2023

document

GDTS: GAN-Based Distributed Tabular Synthesizer

Zhao, Z. (author), Birke, Robert (author), Chen, Lydia Y. (author)

Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. While learning image GANs on Federated Learning (FL) and Multi-Discriminator (MD) systems has just been demonstrated, it is unknown if tabular GANs can be learned...

conference paper 2023

document

FCT-GAN: Enhancing Global Correlation of Table Synthesis via Fourier Transform

Zhao, Z. (author), Birke, Robert (author), Chen, Lydia Y. (author)

An alternative method for sharing knowledge while complying with strict data access regulations, such as the European General Data Protection Regulation (GDPR), is the emergence of synthetic tabular data. Mainstream table synthesizers utilize methodologies derived from Generative Adversarial Networks (GAN). Although several state-of-the-art ...

conference paper 2023

document

AGIC: Approximate Gradient Inversion Attack on Federated Learning

Xu, J. (author), Hong, C. (author), Huang, J. (author), Chen, Lydia Y. (author), Decouchant, Jérémie (author)

Federated learning is a private-by-design distributed learning paradigm where clients train local models on their own data before a central server aggregates their local updates to compute a global model. Depending on the aggregation method used, the local updates are either the gradients or the weights of local learning models, e.g., FedAvg...

conference paper 2023

document

Maverick Matters: Client Contribution and Selection in Federated Learning

Huang, J. (author), Hong, C. (author), Liu, Yang (author), Chen, Lydia Y. (author), Roos, S. (author)

Federated learning (FL) enables collaborative learning between parties, called clients, without sharing the original and potentially sensitive data. To ensure fast convergence in the presence of such heterogeneous clients, it is imperative to timely select clients who can effectively contribute to learning. A realistic but overlooked case of...

conference paper 2023

document

Fast DRL-based scheduler configuration tuning for reducing tail latency in edge-cloud jobs

Wen, Shilin (author), Han, Rui (author), Liu, Chi Harold (author), Chen, Lydia Y. (author)

Edge-cloud applications are rapidly prevailing in recent years and pose the challenge of using both resource-strenuous edge devices and elastic cloud resources under dynamic workloads. Efficient resource allocation on edge-cloud jobs via cluster schedulers (e.g. Kubernetes/Volcano scheduler) is essential to guarantee their performance, e.g....

journal article 2023

document

FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge

Luopan, Yaxin (author), Han, Rui (author), Zhang, Qinglong (author), Liu, Chi Harold (author), Wang, Guoren (author), Chen, Lydia Y. (author)

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral of our daily life. When tackling the evolving learning tasks in real world, such as classifying different types of objects, DNNs face the challenge to continually retrain themselves according to the tasks on different edge devices....

conference paper 2023

document

EdgeVisionBench: A Benchmark of Evolving Input Domains for Vision Applications at Edge

Zhang, Qinglong (author), Han, Rui (author), Liu, Chi Harold (author), Wang, Guoren (author), Chen, Lydia Y. (author)

Vision applications powered by deep neural networks (DNNs) are widely deployed on edge devices and solve the learning tasks of incoming data streams whose class label and input feature continuously evolve, known as domain shift. Despite its prominent presence in real-world edge scenarios, existing benchmarks used by domain adaptation methods...

conference paper 2023

document

EDGETUNE: Inference-Aware Multi-Parameter Tuning

Rocha, Isabelly (author), Felber, Pascal (author), Schiavoni, Valerio (author), Chen, Lydia Y. (author)

Deep Neural Networks (DNNs) have demonstrated impressive performance on many machine-learning tasks such as image recognition and language modeling, and are becoming prevalent even on mobile platforms. Despite so, designing neural architectures still remains a manual, time-consuming process that requires profound domain knowledge. Recently,...

conference paper 2022

document

Aergia: leveraging heterogeneity in federated learning systems

Cox, B.A. (author), Chen, Lydia Y. (author), Decouchant, Jérémie (author)

Federated Learning (FL) is a popular deep learning approach that prevents centralizing large amounts of data, and instead relies on clients that update a global model using their local datasets. Classical FL algorithms use a central federator that, for each training round, waits for all clients to send their model updates before aggregating them...

conference paper 2022

document

Memory-aware and context-aware multi-DNN inference on the edge

Cox, B.A. (author), Birke, Robert (author), Chen, Lydia Y. (author)

Deep neural networks (DNNs) are becoming the core components of many applications running on edge devices, especially for real time image-based analysis. Increasingly, multi-faced knowledge is extracted by executing multiple DNNs inference models, e.g., identifying objects, faces, and genders from images. It is of paramount importance to...

journal article 2022

document

Targeted Influence with Community and Gender-Aware Seeding

Styczen, MacIej (author), Chen, Bing Jyue (author), Teng, Ya Wen (author), Pignolet, Yvonne Anne (author), Chen, Lydia Y. (author), Yang, De Nian (author)

When spreading information over social networks, seeding algorithms selecting users to start the dissemination play a crucial role. The majority of existing seeding algorithms focus solely on maximizing the total number of reached nodes, overlooking the issue of group fairness, in particular, gender imbalance. To tackle the challenge of...

conference paper 2022

document

Federated Learning for Tabular Data: Exploring Potential Risk to Privacy

Wu, Han (author), Zhao, Z. (author), Chen, Lydia Y. (author), van Moorsel, Aad (author)

Federated Learning (FL) has emerged as a potentially powerful privacy-preserving machine learning method-ology, since it avoids exchanging data between participants, but instead exchanges model parameters. FL has traditionally been applied to image, voice and similar data, but recently it has started to draw attention from domains including...

conference paper 2022

document

Permutation-Invariant Tabular Data Synthesis

Zhu, Yujin (author), Zhao, Z. (author), Birke, Robert (author), Chen, Lydia Y. (author)

Tabular data synthesis is an emerging approach to circumvent strict regulations on data privacy while discovering knowledge through big data. Although state-of-the-art AI-based tabular data synthesizers, e.g., table-GAN, CTGAN, TVAE, and CTAB-GAN, are effective at generating synthetic tabular data, their training is sensitive to column...

conference paper 2022

document

Federated Learning With Heterogeneity-Aware Probabilistic Synchronous Parallel on Edge

Zhao, Jianxin (author), Han, Rui (author), Yang, Yongkai (author), Catterall, Benjamin (author), Liu, Chi Harold (author), Chen, Lydia Y. (author), Mortier, Richard (author), Crowcroft, Jon (author), Wang, Liang (author)

With the massive amount of data generated from mobile devices and the increase of computing power of edge devices, the paradigm of Federated Learning has attracted great momentum. In federated learning, distributed and heterogeneous nodes collaborate to learn model parameters. However, while providing benefits such as privacy by design and...

journal article 2022

document

Lightweight and Accurate DNN-Based Anomaly Detection at Edge

Zhang, Qinglong (author), Han, Rui (author), Xin, Gaofeng (author), Liu, Chi Harold (author), Wang, Guoren (author), Chen, Lydia Y. (author)

Deep neural networks (DNNs) have been showing significant success in various anomaly detection applications such as smart surveillance and industrial quality control. It is increasingly important to detect anomalies directly on edge devices, because of high responsiveness requirements and tight latency constraints. The accuracy of DNN-based...

journal article 2022