发表机构
Eindhoven University of Technology; University of Wuppertal（埃因霍温理工大学; 伍珀塔尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对PPM领域基础模型在线持续微调的冷启动问题，提出COMPASS框架，通过自适应子空间与漂移检测技术实现更优性能，且计算开销可接受。
AI 中文摘要
预测过程监控（Predictive Process Monitoring，PPM）模型正越来越多地部署在概念漂移会随时间导致底层过程分布发生偏移的动态环境中。尽管近期研究已转向在线持续学习，但现有方法完全从头开始训练紧凑的特定任务网络，遗留了持续的冷启动问题。基础模型（Foundation Models，FMs）为该问题提供了极具吸引力的解决方案，但其在过程挖掘领域的持续微调仍未被探索。我们提出COMPASS（基于基础模型的在线持续PPM与自适应子空间，Continual Online foundation Model-based PPM with Adaptive SubSpaces），这是首个针对PPM进行基础模型在线持续微调的框架。COMPASS采用损失平台漂移检测方法，自主识别事件流中的任务边界，并维护包含预训练方向和特定任务方向的统一知识子空间。我们在9个涵盖合成与真实世界概念漂移场景的事件流上对所提方法进行评估，涉及无任务和有任务设置，使用多种骨干模型并对所有方法采用一致的超参数调优。我们的方法在9个数据集上的表现优于3种非基础模型的SOTA（State-of-the-Art，当前最优）竞争对手和2种更新策略基线，在呈现周期性漂移和复杂长时运行案例的事件流上获得了尤其显著的提升，同时相比非基础模型竞争对手产生的计算开销处于可接受范围内。
英文摘要
Predictive Process Monitoring (PPM) models are increasingly deployed in dynamic environments where concept drift causes the underlying process distribution to shift over time. While recent work has moved toward online continual learning, existing methods train compact, task-specific networks entirely from scratch, leaving a persistent cold-start problem. Foundation Models (FMs) offer a compelling solution to this problem, but their continual fine-tuning in the process mining domain remains unexplored. We propose COMPASS (Continual Online foundation Model-based PPM with Adaptive SubSpaces), the first framework for online continual fine-tuning of FMs for PPM. COMPASS adapts loss-plateau drift detection to autonomously identify task boundaries in event streams and maintains a unified knowledge subspace including both pre-trained and task-specific directions. We evaluate our approach on nine event streams covering synthetic and real-world concept drift scenarios, across task-free and task-aware settings with multiple backbones and with consistent hyperparameter tuning across all methods. Our approach outperforms three SOTA non-FM competitors and two update strategy baselines, with particularly strong gains on streams exhibiting recurrent drift and complex, long-running cases, while incurring acceptable computational overhead compared to the non-FM competitors.
CommentsThis paper has been accepted at the SCL Workshop at ECML PKDD 2026 in Naples, Italy
