7 papers
Layers Matter: Why Continual Learning Regularization Should Be Layer-Adaptive
Brian B. Moser, Ahmed Anwar, Tobias Christian Nauen +5
Continual learning regularizers like EWC fight forgetting by penalizing changes from previous-task parameters with per-parameter importance, typically diagonal Fisher values. Per-p…
The Gentle Collapse: Distributional Metrics for Continual Learning
Ahmed Anwar, Andreas Wagner, Federico Raue +2
Accuracy degradation is the standard metric for Catastrophic Forgetting (CF), however, it records only whether forgetting occurred or not. It saturates at the extremes and collapse…
TextTeacher: What Can Language Teach About Images?
Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser +3
The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can…
Addressing Heterogeneity in Federated Learning: Challenges and Solutions for a Shared Production Environment
Tatjana Legler, Vinit Hegiste, Ahmed Anwar +1
Federated learning (FL) has emerged as a promising approach to training machine learning models across decentralized data sources while preserving data privacy, particularly in man…
FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Data
Ahmed Anwar, Brian Moser, Dayananda Herurkar +4
The emergence of federated learning (FL) presents a promising approach to leverage decentralized data while preserving privacy. Furthermore, the combination of FL and anomaly detec…
Federated Learning for Blind Image Super-Resolution
Brian B. Moser, Ahmed Anwar, Federico Raue +2
Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, w…