Summary of Hoeg: a New Approach For Object-centric Predictive Process Monitoring, by Tim K. Smit et al.
HOEG: A New Approach for Object-Centric Predictive Process Monitoring
by Tim K. Smit, Hajo A. Reijers, Xixi Lu
First submitted to arxiv on: 8 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary In this paper, researchers propose the Heterogeneous Object Event Graph encoding (HOEG) to predict future states of ongoing process executions, such as forecasting remaining time. HOEG integrates events and objects into a graph structure with diverse node types without aggregating object features, creating a more nuanced representation. The authors adopt a heterogeneous Graph Neural Network architecture that incorporates these diverse object features in prediction tasks. To evaluate the performance and scalability of HOEG, they benchmark it against two established graph-based encodings and two baseline models using three Object-Centric Event Logs (OCELs), including one from a real-life process at a major Dutch financial institution. The results show that HOEG competes well with existing models and surpasses them when OCELs contain informative object attributes and event-object interactions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Predictive Process Monitoring is about predicting what will happen next in a process, like how much time is left. This paper uses special data called Object-Centric Event Logs to help with this prediction. They create a new way to understand this data by putting events and objects into a graph structure. Then they use a special kind of AI model to make predictions. To see if their idea works well, they compare it to other ways of doing things using three different sets of data. The results show that their approach is good and gets even better when the data has useful information about objects and events. |
Keywords
» Artificial intelligence » Graph neural network
