paper-with-me

Papers

ProcK: Machine Learning for Knowledge-Intensive Processes

2021-09-10 · Tobias Jacobs, Jingyi Yu, Julia Gastinger, Timo Sztyler

We present a novel methodology to build powerful predictive process models. Our method, denoted ProcK (Process & Knowledge), relies not only on sequential input data in the form of event logs, but can learn to use a knowledge graph to incorporate information about the attribute values of the events and their mutual relationships. The idea is realized by mapping event attributes to nodes of a knowledge graph and training a sequence model alongside a graph neural network in an end-to-end fashion. This hybrid approach substantially enhances the flexibility and applicability of predictive process monitoring, as both the static and dynamic information residing in the databases of organizations can be directly taken as input data. We demonstrate the potential of ProcK by applying it to a number of predictive process monitoring tasks, including tasks with knowledge graphs available as well as an existing process monitoring benchmark where no such graph is given. The experiments provide evidence that our methodology achieves state-of-the-art performance and improves predictive power when a knowledge graph is available.

📄 PDF Abstract BibTeX arXiv:2109.04881

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeBIG-bench Machine LearningGraph Neural NetworkKnowledge GraphsPredictive Process Monitoring

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

SPROCKET: Extending ROCKET to Distance-Based Time-Series Transformations With Prototypes

2025-12-09 · Nicholas Harner arxiv

Classical Time Series Classification algorithms are dominated by feature engineering strategies. One of the most prominent of these transforms is ROCKET, which achieves strong performance through random kernel features. …

Time Series ClassificationFeature Engineering

DeepROCK: Error-controlled interaction detection in deep neural networks

2023-09-26 · Winston Chen, William Stafford Noble, Yang Young Lu

The complexity of deep neural networks (DNNs) makes them powerful but also makes them challenging to interpret, hindering their applicability in error-intolerant domains. Existing methods attempt to reason about the inte…

scientific discovery

Making Sense of Knowledge Intensive Processes: an Oil & Gas Industry Scenario

2024-01-31 · Juliana Jansen Ferreira, Vinícius Segura, Ana Fucs, Rogério de Paula

Sensemaking is a constant and ongoing process by which people associate meaning to experiences. It can be an individual process, known as abduction, or a group process by which people give meaning to collective experienc…

Decision Making

CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation

2026-02-09 · Jitian Zhao, Changho Shin, Tzu-Heng Huang, Satya Sai Srinath Namburi GNVV 외 arxiv

LLM-as-a-judge ensembles are the standard paradigm for scalable evaluation, but their aggregation mechanisms suffer from a fundamental flaw: they implicitly assume that judges provide independent estimates of true qualit…

Binary Classification

ProcessGPT: Transforming Business Process Management with Generative Artificial Intelligence

2023-05-29 · Amin Beheshti, Jian Yang, Quan Z. Sheng, Boualem Benatallah 외

Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is trained on massive amounts of text data and us…

Decision MakingManagement