Chameleons do not Forget: Prompt-Based Online Continual Learning for Next Activity Prediction

TL;DR

This paper introduces CNAPwP, a prompt-based continual learning method for next activity prediction that effectively mitigates catastrophic forgetting in dynamic environments with concept drifts.

Contribution

It adapts the DualPrompt algorithm for process prediction, introduces new datasets with recurring drifts, and proposes a task-specific forgetting metric.

Findings

CNAPwP achieves state-of-the-art or competitive results on multiple datasets.

The method effectively mitigates catastrophic forgetting in environments with concept drifts.

Open-source implementation and datasets are provided for reproducibility.

Abstract

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.