101 citations · 258 across the 19 of their papers we have counts for
19 papers
BatMan-CLR: Making Few-shots Meta-Learners Resilient Against Label Noise
Jeroen M. Galjaard, Robert Birke, Juan Perez +1
The negative impact of label noise is well studied in classical supervised learning yet remains an open research question in meta-learning. Meta-learners aim to adapt to unseen lea…
A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms
Cristina Silvano, Daniele Ielmini, Fabrizio Ferrandi +19
Recent trends in deep learning (DL) have made hardware accelerators essential for various high-performance computing (HPC) applications, including image classification, computer vi…
Model-Agnostic Federated Learning
Gianluca Mittone, Walter Riviera, Iacopo Colonnelli +2
Since its debut in 2016, Federated Learning (FL) has been tied to the inner workings of Deep Neural Networks (DNNs). On the one hand, this allowed its development and widespread us…
Experimenting with Emerging RISC-V Systems for Decentralised Machine Learning
Gianluca Mittone, Nicolò Tonci, Robert Birke +10
Decentralised Machine Learning (DML) enables collaborative machine learning without centralised input data. Federated Learning (FL) and Edge Inference are examples of DML. While to…
Permutation-Invariant Tabular Data Synthesis
Yujin Zhu, Zilong Zhao, Robert Birke +1
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 tab…
FCT-GAN: Enhancing Table Synthesis via Fourier Transform
Zilong Zhao, Robert Birke, Lydia Y. Chen
Synthetic tabular data emerges as an alternative for sharing knowledge while adhering to restrictive data access regulations, e.g., European General Data Protection Regulation (GDP…
CTAB-GAN+: Enhancing Tabular Data Synthesis
Zilong Zhao, Aditya Kunar, Robert Birke +1
While data sharing is crucial for knowledge development, privacy concerns and strict regulation (e.g., European General Data Protection Regulation (GDPR)) limit its full effectiven…
DTGAN: Differential Private Training for Tabular GANs
Aditya Kunar, Robert Birke, Zilong Zhao +1
Tabular generative adversarial networks (TGAN) have recently emerged to cater to the need of synthesizing tabular data -- the most widely used data format. While synthetic tabular…
Fed-TGAN: Federated Learning Framework for Synthesizing Tabular Data
Zilong Zhao, Robert Birke, Aditya Kunar +1
Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training da…
Enhancing Robustness of On-line Learning Models on Highly Noisy Data
Zilong Zhao, Robert Birke, Rui Han +4
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…
CTAB-GAN: Effective Table Data Synthesizing
Zilong Zhao, Aditya Kunar, Hiek Van der Scheer +2
While data sharing is crucial for knowledge development, privacy concerns and strict regulation (e.g., European General Data Protection Regulation (GDPR)) unfortunately limit its f…
End-to-End Learning from Noisy Crowd to Supervised Machine Learning Models
Taraneh Younesian, Chi Hong, Amirmasoud Ghiassi +2
Labeling real-world datasets is time consuming but indispensable for supervised machine learning models. A common solution is to distribute the labeling task across a large number…
PipeTune: Pipeline Parallelism of Hyper and System Parameters Tuning for Deep Learning Clusters
Isabelly Rocha, Nathaniel Morris, Lydia Y. Chen +3
DNN learning jobs are common in today's clusters due to the advances in AI driven services such as machine translation and image recognition. The most critical phase of these jobs…
TrustNet: Learning from Trusted Data Against (A)symmetric Label Noise
Amirmasoud Ghiassi, Taraneh Younesian, Robert Birke +1
Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. Robustness to label noise is a critical property for weakly-supervis…
ExpertNet: Adversarial Learning and Recovery Against Noisy Labels
Amirmasoud Ghiassi, Robert Birke, Rui Han +1
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 por…
QActor: On-line Active Learning for Noisy Labeled Stream Data
Taraneh Younesian, Zilong Zhao, Amirmasoud Ghiassi +2
Noisy labeled data is more a norm than a rarity for self-generated content that is continuously published on the web and social media. Due to privacy concerns and governmental regu…
RAD: On-line Anomaly Detection for Highly Unreliable Data
Zilong Zhao, Robert Birke, Rui Han +4
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…
Differential Approximation and Sprinting for Multi-Priority Big Data Engines
Robert Birke, Isabelly Rocha, Juan Perez +3
Today's big data clusters based on the MapReduce paradigm are capable of executing analysis jobs with multiple priorities, providing differential latency guarantees. Traces from pr…
WiSE-ALE: Wide Sample Estimator for Approximate Latent Embedding
Shuyu Lin, Ronald Clark, Robert Birke +2
Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we deri…