Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring
For predictive process monitoring, this work provides a unified solution to full event sequence generation, addressing a gap left by component-task approaches, with strong empirical results.
The paper introduces GGATN, a Transformer-based model that generates full event sequences with structural constraints (transition feasibility, temporal order, termination, attribute consistency) in a single pass, achieving zero hallucinated activities and zero attribute inconsistency on six benchmark logs, outperforming LLM baselines in sequence similarity and control flow metrics.
Structurally constrained event sequence generation remains challenging because generated paths must preserve transition feasibility, temporal order, termination, and attribute consistency. In predictive process monitoring (PPM), this challenge appears as full event sequence generation, whereas existing work mainly addresses component tasks such as next activity, remaining time, outcome, and attribute prediction. This paper proposes the Graph Grounded Cross Attention Transformer Neural Network (GGATN) for this unified PPM task. GGATN uses a global process graph as structured activity memory, contextualizes sequence positions through Transformer self attention, and injects process topology through graph grounded cross attention. Unlike autoregressive decoding, GGATN generates activities, timestamps, length, and event level and sequence level attributes in a single pass, followed by Viterbi style graph constrained decoding for feasible paths and explicit termination. Experiments on six benchmark event logs show more reliable generation quality than local instruction prompted LLM baselines. GGATN achieves strong performance on sequence similarity, Damerau Levenshtein similarity, bigram based control flow similarity, and duration distribution, while maintaining zero hallucinated activities and zero sequence level attribute inconsistency. Ablation analyses confirm the global graph encoder as a stable structural prior. Interpretability analyses show how graph structure, sequence context, feedback refinement, and constrained decoding shape generation.