10 papers
AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors
Maher Boughdiri, Mounira Msahli, Albert Bifet
Deep neural networks (DNNs) have shown outstanding performance in visual recognition tasks within vision sensor networks; however, they are still vulnerable to adversarial manipula…
A Framework for Evaluating and Benchmarking Concept Drift Detection Methods
Vitor Cerqueira, Heitor Murilo Gomes, Marco Heyden +2
Data stream mining is fundamentally challenged by concept drift, where distributional changes can degrade model performance. Despite the proliferation of drift detection methods, p…
PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models
Mustafa Hayri Bilgin, Mariam Barry, Albert Bifet +2
Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously ac…
CapyMOA: Efficient Machine Learning for Data Streams and Online Continual Learning in Python
Heitor Murilo Gomes, Anton Lee, Nuwan Gunasekara +9
CapyMOA is an open-source Python library for efficient machine learning on data streams and online continual learning. It provides a structured framework for real-time learning, su…
Policy Gradient with Adaptive Entropy Annealing for Continual Fine-Tuning
Yaqian Zhang, Bernhard Pfahringer, Eibe Frank +1
Despite their success, large pretrained vision models remain vulnerable to catastrophic forgetting when adapted to new tasks in class-incremental settings. Parameter-efficient fine…
Quantum Re-Uploading for Calorimetry: Optimized Architectures with Extended Expressivity
Léa Cassé, Bernhard Pfahringer, Albert Bifet +1
Near-term quantum machine learning must balance expressivity, optimization, and hardware constraints. We study quantum re-uploading units (QRUs) as compact circuits and compare the…