Adversarial Graph Unlearning
AvailableGraph Neural Networks, Machine Unlearning, Adversarial ML·Proposal
Theses
Send an email to andrea@cs.au.dk if you are interested in one of the available theses.
AvailableSoftware Engineering, Open Source, ERASURE
A thesis focused on debugging, refactoring, and documenting the ERASURE machine unlearning framework, lowering the skill floor so that researchers can adopt it without reading the source code.
AvailableFairness, ERASURE, Trustworthy AI
Can selectively forgetting training data improve or harm model fairness? This thesis investigates the interplay between machine unlearning and fairness metrics across multiple domains using the ERASURE framework.
Machine Unlearning on a Multimodal Videogame dataset
AvailableMultimodal, Machine Unlearning, Datasets·Proposal
Machine Unlearning Applied to Time Series and Human Activity Recognition
CompletedTime Series, Human Activity Recognition, Machine Unlearning
Beyond the Systematic Evaluation of Large Language Models: From Theory to Practical Analysis of Results
CompletedLLMs, Evaluation, Benchmarking
HybridKAN: Leveraging Multi-Sized Sub-MLPs for Enhanced Performance
CompletedKolmogorov-Arnold Networks, Neural Architectures, MLP
From ERASURE to Evaluation of Machine Unlearning Techniques
CompletedMachine Unlearning, ERASURE, Evaluation
Recent Advances in Chain-of-Thought Prompting: Current Trends and Automation Approaches
CompletedChain-of-Thought, Prompting, LLMs
Nothing here matches that search.