Description
A regularization criterion that, differently from dropout and its variants, is deterministic rather than random. It grounds on the empirical evidence that feature descriptors with larger L2-norm and highly-active nodes are strongly correlated to confident class predictions. Thus, the criterion guides towards dropping a percentage of the most active nodes of the descriptors, proportionally to the estimated class probability
Papers Using This Method
Partition Generative Modeling: Masked Modeling Without Masks2025-05-24Smooth optimization algorithms for global and locally low-rank regularizers2025-05-09Knowledge-Aided Semantic Communication Leveraging Probabilistic Graphical Modeling2024-08-08Model Predictive Simulation Using Structured Graphical Models and Transformers2024-06-28Digital Twinning of a Pressurized Water Reactor Startup Operation and Partial Computational Offloading in In-network Computing-Assisted Multiaccess Edge Computing2024-06-24A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning2024-06-16Differentiable Proximal Graph Matching2024-05-26Fast-PGM: Fast Probabilistic Graphical Model Learning and Inference2024-05-24Prompt Customization for Continual Learning2024-04-28Solving the Clustering Reasoning Problems by Modeling a Deep-Learning-Based Probabilistic Model2024-03-05MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration2023-11-14Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data2023-10-30Approximate Implication for Probabilistic Graphical Models2023-10-21Probabilistic Modeling of Human Teams to Infer False Beliefs2023-10-19Delta-AI: Local objectives for amortized inference in sparse graphical models2023-10-03Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning2023-07-11Approximate inference of marginals using the IBIA framework2023-06-01On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models2023-05-27Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models2023-03-23Neural Graph Revealers2023-02-27