Understanding Rollout Error in Graph World Models

• URL: http://arxiv.org/abs/2606.27780v1
• Date: Fri, 26 Jun 2026 07:11:29 GMT
• Title: Understanding Rollout Error in Graph World Models
• Abstract summary: This paper studies long-horizon rollout error in Graph World Models (GWMs)<n>We formulate a unified fixed-edge and dynamic-edge GWM framework with action nodes for node-, edge-, and graph-level decisions.<n>We propose Error-Aware GWM, which combines spectral regularization, rollout consistency, and critical-node weighting.
• Score: 2.571318992830046
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World models are often used for planning by rolling learned dynamics forward. Many planning environments, however, are not vectors or images; they are graphs of agents, tools, skills, routes, and dependencies. In these settings, a local prediction error may stay local or spread through the graph, and the failure mode changes again when edges are predicted rather than fixed. This paper studies long-horizon rollout error in Graph World Models (GWMs). We formulate a unified fixed-edge and dynamic-edge GWM framework with action nodes for node-, edge-, and graph-level decisions. We develop graph-valued rollout bounds that separate topology-induced amplification from model-induced amplification, and we introduce a joint node-edge operator for dynamic-edge rollouts. Guided by the analysis, we propose Error-Aware GWM, which combines spectral regularization, rollout consistency, and critical-node weighting. Across synthetic topologies and heterogeneous agent-graph testbeds, rollout error and planning regret grow with horizon, dynamic-edge training is needed when structure evolves, and Error-Aware GWM prevents long-horizon divergence while preserving prediction accuracy. Real-world graph benchmarks clarify the scope of GWMs: they are most useful for dynamic graph rollout and agent planning, while specialized graph models remain strong on static or sparse prediction tasks.

Related papers

• Defending against Model Extraction for GNNs with Model Reprogramming [57.82196268649236]
  Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (ML)<n>Still, their black-box deployment exposes them to Model Extraction (ME) attacks.<n>Existing defenses suffer from a critical ''Euclidean bias''<n>We propose GraphRP, a proactive defense framework that repurposes Model Reprogramming for security.
  arXiv  Detail & Related papers  (2026-08-11T23:20:15Z)
• Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs [43.39867023055097]
  We propose SG-JEPA, a joint spiking embedding predictive architecture for large-scale dynamic graphs.<n> SG-JEPA partitions nodes into context and target sets along the temporal dimension to learn embeddings that are predictive of each other.<n>Experiments demonstrate that SG-JEPA achieves competitive or even superior performance over discriminative baselines on node classification.
  arXiv  Detail & Related papers  (2026-07-20T18:02:04Z)
• Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation [80.56829418752513]
  Language models (LMs) generalize flexibly via a unified input-output interface, motivating recent attempts to adapt LMs to graph tasks.<n>We propose a novel weight-level information injection paradigm for adapting LMs to graph tasks.<n>We introduce GaRA, a Graph-aware LoRA generation model, which constructs low-rank weight updates conditioned on the original graph structures.
  arXiv  Detail & Related papers  (2026-06-21T10:40:33Z)
• Fine-Grained Graph Generation through Latent Mixture Scheduling [16.95910326345246]
  We introduce a novel conditional variational autoencoder for fine-grained structural control in graph generation.<n>The approach refines the decoder's latent space by dynamically aligning graph- and property-driven representations to improve both graph fidelity and control satisfaction.
  arXiv  Detail & Related papers  (2026-05-04T16:23:01Z)
• Graph-RHO: Critical-path-aware Heterogeneous Graph Network for Long-Horizon Flexible Job-Shop Scheduling [26.97705087364345]
  Graph-RHO is a novel critical-path-aware graph-based RHO framework.<n>We introduce a topology-aware heterogeneous graph network that encodes subproblems as operation-machine graphs with multi-relational edges.<n>We incorporate a critical-path-aware mechanism that injects inductive biases during training to distinguish highly sensitive bottleneck operations from robust ones.
  arXiv  Detail & Related papers  (2026-04-11T07:35:09Z)
• Graph Your Own Prompt [44.358377952850994]
  Graph Consistency Regularization (GCR) is a framework that injects relational graph structures, derived from model predictions, into the learning process.<n>GCR promotes cleaner feature structure, stronger intra-class cohesion, and improved generalization, offering a new perspective on learning from prediction structure.
  arXiv  Detail & Related papers  (2025-09-27T15:45:07Z)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation [13.317620250521124]
  Source-free domain adaptation is a crucial machine learning topic, as it contains numerous applications in the real world. Recent graph neural network (GNN) approaches can suffer from serious performance decline due to domain shift and label scarcity. We propose a novel method named Graph Diffusion-based Alignment with Jigsaw (GALA), tailored for source-free graph domain adaptation.
  arXiv  Detail & Related papers  (2024-10-22T01:32:46Z)
• Discrete Graph Auto-Encoder [52.50288418639075]
  We introduce a new framework named Discrete Graph Auto-Encoder (DGAE) We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model.
  arXiv  Detail & Related papers  (2023-06-13T12:40:39Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)
• Unsupervised Graph Embedding via Adaptive Graph Learning [85.28555417981063]
  Graph autoencoders (GAEs) are powerful tools in representation learning for graph embedding. In this paper, two novel unsupervised graph embedding methods, unsupervised graph embedding via adaptive graph learning (BAGE) and unsupervised graph embedding via variational adaptive graph learning (VBAGE) are proposed. Experimental studies on several datasets validate our design and demonstrate that our methods outperform baselines by a wide margin in node clustering, node classification, and graph visualization tasks.
  arXiv  Detail & Related papers  (2020-03-10T02:33:14Z)

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.