no code implementations • 1 Mar 2024 • Sana Ebrahimi, Kaiwen Chen, Abolfazl Asudeh, Gautam Das, Nick Koudas
Pre-trained Large Language Models (LLMs) have significantly advanced natural language processing capabilities but are susceptible to biases present in their training data, leading to unfair outcomes in various applications.
no code implementations • 8 Feb 2024 • Naiqing Guan, Nick Koudas
Modern machine learning models require large labelled datasets to achieve good performance, but manually labelling large datasets is expensive and time-consuming.
no code implementations • 1 Nov 2023 • Naiqing Guan, Kaiwen Chen, Nick Koudas
This evaluation unveils both the strengths and limitations of contemporary PLMs in LF design.
1 code implementation • 24 Mar 2022 • Tommaso Teofili, Donatella Firmani, Nick Koudas, Vincenzo Martello, Paolo Merialdo, Divesh Srivastava
CERTA builds on a probabilistic framework that aims at computing the explanations evaluating the outcomes produced by using perturbed copies of the input records.
no code implementations • 23 Nov 2020 • Zhaoyue Chen, Nick Koudas, Zhe Zhang, Xiaohui Yu
For the case of NN, we propose algorithms to train the network taking normalized data as the input.
no code implementations • 2 Mar 2020 • Yueting Chen, Xiaohui Yu, Nick Koudas
We propose two techniques, MFS and SSG, to organize all detected objects in the intermediate data generation layer, which effectively, given the queries, minimizes the number of objects and frames that have to be considered during query evaluation.
no code implementations • 24 Feb 2020 • Nick Koudas, Raymond Li, Ioannis Xarchakos
We demonstrate that the application of the techniques proposed in conjunction with declarative queries on video streams can dramatically increase the frame processing rate and speed up query processing by at least two orders of magnitude.
no code implementations • 24 Mar 2019 • Shohedul Hasan, Saravanan Thirumuruganathan, Jees Augustine, Nick Koudas, Gautam Das
Selectivity estimation - the problem of estimating the result size of queries - is a fundamental problem in databases.
no code implementations • 24 Mar 2019 • Saravanan Thirumuruganathan, Shohedul Hasan, Nick Koudas, Gautam Das
We use deep generative models, an unsupervised learning based approach, to learn the data distribution faithfully such that aggregate queries could be answered approximately by generating samples from the learned model.