EHHN is a heterogeneous hypergraph network with dual micro-spatial and macro-evolution streams that achieves top accuracy and F1 on four OCEL benchmarks while cutting GPU memory use by up to 24x versus graph baselines.
arXiv preprint arXiv:2104.00721
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
GGATN combines graph grounding with transformer self- and cross-attention to generate full event sequences, timestamps, length, and attributes in a single pass followed by Viterbi-style constrained decoding, outperforming prompted LLM baselines on six logs with zero hallucinated activities.
N-gram models equipped with a dynamic promotion ensemble match or exceed the accuracy of neural networks for next-activity prediction in event logs while using substantially fewer resources.
citing papers explorer
-
EHHN: An Event-driven Heterogeneous Hypergraph Network for Object-Centric Next Activity Prediction
EHHN is a heterogeneous hypergraph network with dual micro-spatial and macro-evolution streams that achieves top accuracy and F1 on four OCEL benchmarks while cutting GPU memory use by up to 24x versus graph baselines.
-
Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring
GGATN combines graph grounding with transformer self- and cross-attention to generate full event sequences, timestamps, length, and attributes in a single pass followed by Viterbi-style constrained decoding, outperforming prompted LLM baselines on six logs with zero hallucinated activities.
-
Promoting Simple Agents: Ensemble Methods for Event-Log Prediction
N-gram models equipped with a dynamic promotion ensemble match or exceed the accuracy of neural networks for next-activity prediction in event logs while using substantially fewer resources.