Fuzzy Trace
"Trace" in scientific research refers to the sequential data representing a process or system's evolution, whether it's user interactions on a website, network communication patterns, or the execution of a computational workflow. Current research focuses on developing efficient methods for analyzing and utilizing these traces, often employing transformer-based architectures and recurrent neural networks for tasks like anomaly detection, prediction, and optimization. This work is significant for improving the performance and interpretability of AI systems, enabling more effective process monitoring, and facilitating deeper understanding of complex systems across diverse domains.
Papers
TRACE: Transformer-based user Representations from Attributed Clickstream Event sequences
William Black, Alexander Manlove, Jack Pennington, Andrea Marchini, Ercument Ilhan, Vilda Markeviciute
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Esraa Elelimy, Adam White, Michael Bowling, Martha White
Conformance Checking of Fuzzy Logs against Declarative Temporal Specifications
Ivan Donadello, Paolo Felli, Craig Innes, Fabrizio Maria Maggi, Marco Montali
TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
Jinyuan Fang, Zaiqiao Meng, Craig Macdonald