Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces Continual Next Activity Prediction with Prompts (CNAPwP), a novel prompt-based online continual learning approach, to address catastrophic forgetting in next activity prediction within dynamic process monitoring environments. CNAPwP adapts the DualPrompt algorithm, using task-specific and shared prompts to maintain performance on previously learned data distributions while adapting to new concept drifts. Experiments on synthetic and real-world datasets with recurring concept drifts demonstrate that CNAPwP achieves state-of-the-art or competitive results compared to existing baselines, showcasing its effectiveness in mitigating catastrophic forgetting.
Existing process monitoring systems crumble when faced with real-world concept drift, but this new prompt-based approach learns continuously without forgetting.
Predictive process monitoring (PPM) focuses on predicting future process trajectories, including next activity predictions. This is crucial in dynamic environments where processes change or face uncertainty. However, current frameworks often assume a static environment, overlooking dynamic characteristics and concept drifts. This results in catastrophic forgetting, where training while focusing merely on new data distribution negatively impacts the performance on previously learned data distributions. Continual learning addresses, among others, the challenges related to mitigating catastrophic forgetting. This paper proposes a novel approach called Continual Next Activity Prediction with Prompts (CNAPwP), which adapts the DualPrompt algorithm for next activity prediction to improve accuracy and adaptability while mitigating catastrophic forgetting. We introduce new datasets with recurring concept drifts, alongside a task-specific forgetting metric that measures the prediction accuracy gap between initial occurrence and subsequent task occurrences. Extensive testing on three synthetic and two real-world datasets representing several setups of recurrent drifts shows that CNAPwP achieves SOTA or competitive results compared to five baselines, demonstrating its potential applicability in real-world scenarios. An open-source implementation of our method, together with the datasets and results, is available at: https://github.com/SvStraten/CNAPwP .