Related papers: McUDI: Model-Centric Unsupervised Degradation Indi…
Classification models play a central role in data-driven decision-making applications such as medical diagnosis, recommendation systems, and risk assessment. Traditional performance metrics, such as accuracy and AUC, focus on overall error…
Machine learning models are widely recognized for their strong performance in forecasting. To keep that performance in streaming data settings, they have to be monitored and frequently re-trained. This can be done with machine learning…
We present a machine unlearning approach that is both retraining- and label-free. Most existing machine unlearning approaches require a model to be fine-tuned to remove information while preserving performance. This is computationally…
Self-supervised learning has emerged as a method for utilizing massive unlabeled data for pre-training models, providing an effective feature extractor for various mobile sensing applications. However, when deployed to end-users, these…
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…
Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe…
In real-time Industrial Internet of Things (IIoT), e.g., monitoring and control scenarios, the freshness of data is crucial to maintain the system functionality and stability. In this paper, we propose an AoI-Aware Deep Learning (AA-DL)…
Quality control is a key activity performed by manufacturing enterprises to ensure products meet quality standards and avoid potential damage to the brand's reputation. The decreased cost of sensors and connectivity enabled an increasing…
Occlusion poses a major challenge for person re-identification (ReID). Existing approaches typically rely on outside tools to infer visible body parts, which may be suboptimal in terms of both computational efficiency and ReID accuracy. In…
Intrusion Detection Systems (IDS) must maintain reliable detection performance under rapidly evolving benign traffic patterns and the continual emergence of cyberattacks, including zero-day threats with no labeled data available. However,…
Anomaly detection for cyber-physical systems (ADCPS) is crucial in identifying faults and potential attacks by analyzing the time series of sensor measurements and actuator states. However, current methods lack adaptation to data…
Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the…
Myocardial infarction (MI) is a leading cause of death, and its adverse outcomes are urgent to predict. Yet ECG-based prognostic models underperform because deep learning requires large, labelled datasets, which are scarce in medicine.…
Performance regressions have a tremendous impact on the quality of software. One way to catch regressions before they reach production is executing performance tests before deployment, e.g., using microbenchmarks, which measure performance…
Robust training with noisy labels is a critical challenge in image classification, offering the potential to reduce reliance on costly clean-label datasets. Real-world datasets often contain a mix of in-distribution (ID) and…
Training deep learning neural networks often requires massive amounts of computational ressources. We propose to sequentially monitor network predictions to trigger retraining only if the predictions are no longer valid. This can reduce…
Monitoring machine learning models once they are deployed is challenging. It is even more challenging to decide when to retrain models in real-case scenarios when labeled data is beyond reach, and monitoring performance metrics becomes…
Failure of mission-critical equipment interrupts production and results in monetary loss. The risk of unplanned equipment downtime can be minimized through Predictive Maintenance of revenue generating assets to ensure optimal performance…
Building a predictive model that rapidly adapts to real-time condition monitoring (CM) signals is critical for engineering systems/units. Unfortunately, many current methods suffer from a trade-off between representation power and agility…
Machine learning is central to modern science, industry, and policy, yet its predictive power often comes at the cost of transparency: we rarely know which input features truly drive a model's predictions. Without such understanding,…