Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring

• URL: http://arxiv.org/abs/2606.18726v1
• Date: Wed, 17 Jun 2026 06:10:27 GMT
• Title: Graph Grounded Cross Attention Transformer Neural Network for Structurally Constrained Full Event Sequence Generation in Predictive Process Monitoring
• Abstract summary: This paper proposes the Graph Grounded Cross Attention Transformer Neural Network.<n>GGATN generates activities, timestamps, length, and event level and sequence level attributes in a single pass.<n>Experiments on six benchmark event logs show more reliable generation quality than local instruction.
• Score: 3.793186450307008
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models [0.0]
  We introduce HOPPER, an end-to-end learnable extension of Linearized Graph Sequence Models.<n>HOPPER learns how hop sequences should be extracted before they are processed by a modern state-space model.<n>We show that HOPPER is state-of-the-art or competitive across the ECHO- Synth benchmark.
  arXiv  Detail & Related papers  (2026-08-10T02:31:46Z)
• GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration [34.588097323063074]
  GraphBit is an engine-orchestrated framework that defines explicitly and deterministically as a directed acyclic graph (DAG)<n>Unlike prompted orchestration, agents in GraphBit operate as typed functions, while a Rust-based engine governs routing, state transitions, and tool invocation, ensuring auditability.<n>A three-tier memory architecture consisting of ephemeral scratch space, structured state, and external connectors isolates context across stages, preventing cascading context that degrades reasoning in long-running pipelines.
  arXiv  Detail & Related papers  (2026-03-08T18:32:28Z)
• GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction [51.83437071408662]
  We propose GLOW, a unified framework for AW performance prediction.<n>GLOW combines the graph-structure modeling capabilities of GNNs with the reasoning power of LLMs.<n>Experiments on FLORA-Bench show that GLOW outperforms state-of-the-art baselines in prediction accuracy and ranking utility.
  arXiv  Detail & Related papers  (2025-12-11T13:30:46Z)
• UniGTE: Unified Graph-Text Encoding for Zero-Shot Generalization across Graph Tasks and Domains [12.05107789697386]
  We introduce UniGTE, an instruction-tuned encoder-decoder framework that unifies structural and semantic reasoning.<n>UniGTE is instruction-tuned on five datasets spanning node-level, edge-level, and graph-level tasks across diverse domains.<n>It achieves new state-of-the-art zero-shot results on node classification, link prediction, graph classification, and graph regression under cross-task and cross-domain settings.
  arXiv  Detail & Related papers  (2025-10-19T15:36:45Z)
• Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoring [6.125909573003906]
  We propose a unified, interpretable GNN framework that advances the state of the art along three key axes.<n>First, we compare prefix-based Graph Convolutional Networks(GCNs) and full trace Graph Attention Networks(GATs) to quantify the performance gap between localized and global modeling.<n>Second, we introduce a novel time decay attention mechanism that constructs dynamic, prediction-centered windows.<n>Third, we embed transition type semantics into edge features to enable fine grained reasoning over structurally ambiguous traces.
  arXiv  Detail & Related papers  (2025-08-13T06:21:42Z)
• A Pure Transformer Pretraining Framework on Text-attributed Graphs [50.833130854272774]
  We introduce a feature-centric pretraining perspective by treating graph structure as a prior. Our framework, Graph Sequence Pretraining with Transformer (GSPT), samples node contexts through random walks. GSPT can be easily adapted to both node classification and link prediction, demonstrating promising empirical success on various datasets.
  arXiv  Detail & Related papers  (2024-06-19T22:30:08Z)
• Learning Point Processes using Recurrent Graph Network [11.445441489156027]
  We present a novel Recurrent Graph Network (RGN) approach for predicting discrete marked event sequences by learning the underlying complex process. The nodes of the Graph Network use LSTM to incorporate past information whereas a Graph Attention Network (GAT Network) introduces strong inductive biases to capture the interaction between these different types of events. Experiments show that the proposed approach improves performance in log-likelihood, prediction and goodness-of-fit tasks with lower time and space complexity compared to state-of-the art Transformer based architectures.
  arXiv  Detail & Related papers  (2022-08-11T10:08:23Z)
• AEGNN: Asynchronous Event-based Graph Neural Networks [54.528926463775946]
  Event-based Graph Neural Networks generalize standard GNNs to process events as "evolving"-temporal graphs. AEGNNs are easily trained on synchronous inputs and can be converted to efficient, "asynchronous" networks at test time.
  arXiv  Detail & Related papers  (2022-03-31T16:21:12Z)
• Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation [109.46348908829697]
  We propose a novel Edit-Invariant Sequence Loss (EISL), which computes the matching loss of a target n-gram with all n-grams in the generated sequence. We conduct experiments on three tasks: machine translation with noisy target sequences, unsupervised text style transfer, and non-autoregressive machine translation.
  arXiv  Detail & Related papers  (2021-06-29T03:59:21Z)
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs [54.13919050090926]
  We propose an end-to-end structural temporal Graph Neural Network model for detecting anomalous edges in dynamic graphs. In particular, we first extract the $h$-hop enclosing subgraph centered on the target edge and propose the node labeling function to identify the role of each node in the subgraph. Based on the extracted features, we utilize Gated recurrent units (GRUs) to capture the temporal information for anomaly detection.
  arXiv  Detail & Related papers  (2020-05-15T09:17:08Z)
• Efficient and Stable Graph Scattering Transforms via Pruning [86.76336979318681]
  Graph scattering transforms ( GSTs) offer training-free deep GCN models that extract features from graph data. The price paid by GSTs is exponential complexity in space and time that increases with the number of layers. The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p) GST approach.
  arXiv  Detail & Related papers  (2020-01-27T16:05:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.