mlsanityData to 7 Oct 2026

PGTNet: A Process Graph Transformer Network for Remaining Time Prediction of Business Process Instances

arXiv 2404.06267 ↗First posted 9 Apr 2024cs.LG cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

We present PGTNet, an approach that transforms event logs into graph datasets and leverages graph-oriented data for training Process Graph Transformer Networks to predict the remaining time of business process instances. PGTNet consistently outperforms state-of-the-art deep learning approaches across a diverse range of 20 publicly available real-world event logs. Notably, our approach is most promising for highly complex processes, where existing deep learning approaches encounter difficulties stemming from their limited ability to learn control-flow relationships among process activities and capture long-range dependencies. PGTNet addresses these challenges, while also being able to consider multiple process perspectives during the learning process.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 16 of its 25 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

16 of 25 references.

References · 16

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  3. 2017Deep Setscited by 1,394
  4. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  5. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  6. 2021Rethinking Graph Transformers with Spectral Attentioncited by 468
  7. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  8. 2022Sign and Basis Invariant Networks for Spectral Graph Representation Learningcited by 176
  9. 2016Predictive Business Process Monitoring with LSTM Neural Networkscited by 103
  10. 2016Predicting Process Behaviour using Deep Learningcited by 59
  11. 2020Deep Learning for Predictive Business Process Monitoring: Review and Benchmarkcited by 45
  12. 2018Survey and cross-benchmark comparison of remaining time prediction methods in business process monitoringcited by 43
4 more
  1. 2021ProcessTransformer: Predictive Business Process Monitoring with Transformer Networkcited by 34
  2. 2017LSTM Networks for Data-Aware Remaining Time Prediction of Business Process Instancescited by 19
  3. 2021Creating Unbiased Public Benchmark Datasets with Data Leakage Prevention for Predictive Process Monitoringcited by 16
  4. 2021A Comparison of Deep-Learning Methods for Analysing and Predicting Business Processescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 7.

13 papers.

Sort:

  1. 2025Directly Follows Graphs Go Predictive Process Monitoring With Graph Neural Networkscited by 3
  2. 2025Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoringcited by 2
  3. 2025Log Optimization Simplification Method for Predicting Remaining Timecited by 1
  4. 2025Predictive Process Monitoring Using Object-centric Graph Embeddingscited by 1
  5. 2026Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approachcited by 1
  6. 2025On the Simplification of Neural Network Architectures for Predictive Process Monitoringcited by 0
  7. 2025Remaining Time Prediction in Outbound Warehouse Processes: A Case Study (Short Paper)cited by 0
  8. 2026Exploring LLM Features in Predictive Process Monitoring for Small-Scale Event-Logscited by 0
  9. 2026Promoting Simple Agents: Ensemble Methods for Event-Log Predictioncited by 0
  10. 2026Mind the Long Tail: Understanding the Difficulty of Delay Detection in Business Processescited by 0
  11. 2026D-TAIA: Domain-Aware LLM Adaptation for Multi-Task Predictive Process Monitoringcited by 0
  12. 2026GNN4PPM: Multi-Target Predictive Process Monitoring with Relational Graph Convolutional Networkscited by 0
1 more
  1. 2026Probabilistic Forecasting of Business Process Executions with Neural Temporal Point Processescited by 0