document

Confidentiality-Preserving Collaborative Bayesian Networks

Mălan, Abel (author)

Effective large-scale process optimization in manufacturing industries requires close cooperation between different parties of human experts who encode their knowledge of related domains as Bayesian network models. For example, parties in the steel industry must collaboratively use their Bayesian networks on process parameters at the maker,...

master thesis 2023

document

Multi-server Asynchronous Federated Learning

Zuo, Yuncong (author)

In federated learning systems, a server maintains a global model trained by a set of clients based on their local datasets. Conventional synchronous FL systems are very sensitive to system heterogeneity since the server needs to wait for the slowest clients in each round. Asynchronous fl partially addresses this bottleneck by dealing with...

master thesis 2023

document

Share your Secrets for Private Forecasting with Vertical Federated Learning

Shankar, Aditya (author)

Vertical federated learning’s (VFL) immense potential for time series forecasting in industrial applications such as predictive maintenance and machine control remains untapped. Critical challenges to be addressed in the manufacturing industry include small and noisy datasets, model explainability, and stringent privacy requirements for training...

master thesis 2023

document

Clustering faces of comic characters: An experimental investigation

Boz, Artun (author)

Face clustering is a subfield of computer vision and pattern recognition with many applications such as face recognition and surveillance. Accurate clustering of faces can also help us to create labeled datasets. However, in the domain of comics, face clustering is not well studied. Therefore, it is uncertain which methods of feature extraction...

bachelor thesis 2023

document

Does text matter?: Extending CLIP with OCR and NLP for image classification and retrieval

Sassoon, Jordan (author)

Contrastive Language-Image Pretraining (CLIP) has gained vast interest due to its impressive performance on a variety of computer vision tasks: image classification, image retrieval, action recognition, feature extraction, and more. The model learns to associate images with their descriptions, a powerful method which allows it to perform well on...

bachelor thesis 2023

document

Controlling Poisson Flow Generative Model: Implementing a class conditional generative model

GEORGIADES, IOANNIS (author)

With the following paper we are planning to present and explore the possibilities of the the newly introduced Poisson Flow Generative Model (PFGM). More specifically, this work aims to introduce the Conditional Poisson Flow Generative Model (CoPFGM), which by extending the existing repository of the PFGM, it will be able to be trained in a way...

bachelor thesis 2023

document

Extending CTAB-GAN+ with StackGAN architecture

Akdemir, Rauf (author)

As privacy regulations (e.g. European General Data Protection Regulation) often prevent valuable flows of data between stakeholders, data synthesis can play a crucial role in sharing captured value in data sets without sharing personal details. Different attempts have been made at solving this problem with Generative Adversarial Networks (GAN)...

bachelor thesis 2023

document

Client self-defense against model poisoning in federated learning

Zhu, Chaoyi (author)

Federated Learning is highly susceptible to backdoor and targeted attacks as participants can manipulate their data and models locally without any oversight on whether they follow the correct process. There are a number of server-side defenses that mitigate the attacks by modifying or rejecting local updates submitted by clients. However, we...

master thesis 2023

document

Meta-Learning with label noise: A step towards label few-shot meta-learning with label noise.

Galjaard, Jeroen (author)

Few-shot learning presents the challenging problem of learning a task with only a few provided examples. Gradient-Based Meta-Learners (GBML) offer a solution for learning such few-shot problems. These learners approach the few-shot problem by learning an initial parameterization that requires only a few adaptation steps for new tasks. Although...

master thesis 2023

document

Champagne Taste on a Beer Budget: Better Budget Utilisation in Multi-label Adversarial Attacks

van Thiel, Erwin (author)

Abstract—Multi-label classification is an important branch of classification problems as in many real world classification scenarios an object can belong to multiple classes simultaneously. Deep learning based classifiers perform well at image classifica- tion but their predictions have shown to be unstable when subject to small input...

master thesis 2022

document

Permutation-Invariant Tabular Data Synthesis

Zhu, Yujin (author)

Tabular data synthesis is a promising approach to circumvent strict regulations on data privacy. Although the state-of-the-art tabular data synthesizers, e.g., table-GAN, CTGAN, TVAE, and CTAB-GAN, are effective at generating synthetic tabular data, they are sensitive to column permutations of input data. In this work, we conduct an impact and...

master thesis 2022

document

LCT-GAN - Improving the efficiency of tabular data synthesis via latent embeddings

Velev, Viktor (author)

In the past decade data-driven approaches have been at the core of many business and research models. In critical domains such as healthcare and banking, data privacy issues are very stringent. Synthetic tabular data is an emerging solution to privacy guarantee concerns. Generative Adversarial Networks (GANs) are one of the emerging solutions...

bachelor thesis 2022

document

Self-supervised Audio-reactive Music Video Synthesis: Measuring and optimizing audiovisual correlation

Brouwer, Hans (author)

Synthesizing audio-reactive videos to accompany music is challenging multi-domain task that requires both a visual synthesis skill-set and an understanding of musical information extraction. In recent years a new flexible class of visual synthesis methods has gained popularity: generative adversarial networks. These deep neural networks can be...

master thesis 2022

document

Approximate Gradient Inversion Attack on Federated Learning

Xu, Jin (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. Unfortunately,...

master thesis 2022

document

UniformGAN: generative adversarial networks in uniform probability spaces: Improving correlation by leveraging integral probability transform

Visser, Marc (author)

Sharing data is becoming increasingly difficult, due to the regulatory constraints imposed by the General Data Protection Regulation (GDPR). Businesses are not allowed to share data which contains privacy sensitive information. Synthetic data generation has emerged as a solution to this problem. State of the art generative adversarial networks ...

bachelor thesis 2022

document

FCT-GAN: Fourier Neural Operator for Global Relation Enhancement in Tabular Data Synthesizing using Generative Adversarial Networks

Keller, Ethan (author)

Since the regularization of data privacy (e.g., GDPR), the effectiveness of data sharing has decreased. A promising technique to circumvent this problem is tabular data synthesis (i.e., the generation of fake tabular data that statistically resembles the original data). However, the state-of-the-art tabular data synthesis model, CTAB-GAN, fails...

bachelor thesis 2022

document

Fairness Information Maximization on social media

Zhang, Zhiyue (author)

The rapid growth of the Internet use has allowed social networks to become the most effective means for marketing, leading to the emergence of "viral marketing" as a business model. The biggest challenge that is facing "viral marketing" is selecting seed users from the whole user set to form a "seed-set" to spread the influence and maximize the...

master thesis 2022

document

Federated learning from non-iid data: Improving accuracy through data-augmentation and communication efficiency

Cornelis, Izaak (author)

Federated learning allows multiple parties to collaboratively develop a deep learning model, without sharing private data. Models can be generated from the most up-to-date data while taking unique and not publicly available data into account. However, the distributed nature of federated learning causes problems too, and clients are not...

master thesis 2022

document

Time series synthesis using GANs - A take on DoppelGANger

Schaap, Auke (author)

With a growing need for data comes a growing need for synthetic data. In this work we reproduce the results of DoppelGANger [16] in synthesising time series data with metadata. We identify a key issue in the comparison made in [16] of DoppelGANger to TimeGAN, RNNs, AR and HMM models, which creates a new avenue of time series synthesis using GANs...

bachelor thesis 2021

document

Multi-Label Gold Asymmetric Loss Correction with Single-Label Regulators

Pene, Cosmin (author)

Multi-label learning is an emerging extension of the multi-class classification where an image contains multiple labels. Not only acquiring a clean and fully labeled dataset in multi-label learning is extremely expensive, but also many of the actual labels are corrupted or missing due to the automated or non-expert annotation techniques. Noisy...

bachelor thesis 2021