SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation

• URL: http://arxiv.org/abs/2607.17288v1
• Date: Sun, 19 Jul 2026 15:09:21 GMT
• Title: SAGA: Synthetic Agentic Graph Architecture for Temporal Benchmark Generation
• Abstract summary: SAGA is a system for generating semantically rich temporal graphs via a four-phase pipeline.<n>It achieves structural realism, semantic richness, and automatic anomaly labeling in a unified framework.<n>The system supports real-time pipeline visualization, interactive multi-domain tuning, and a CLI for large-scale GPU-based experiments.
• Score: 4.0999277836699894
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High quality temporal graph benchmarks with rich semantics and ground-truth anomaly labels are essential for training graph neural networks, yet remain scarce due to privacy constraints and annotation costs. We present SAGA (Synthetic Agentic Graph Architecture), a system for generating large-scale, semantically rich temporal graphs via a four-phase pipeline. Our Skeleton-First, Semantics-Second architecture decouples structure from semantics: (S) an O(1)-per-edge skeleton generator produces power-law graphs; (A) a dispatcher partitions causally ordered time blocks for parallel execution; (G) LLM agents inject domain semantics using RAG-based rule bases across four domains; and (A) a state alignment engine resolves conflicts via temporal replay, yielding anomaly labels as natural byproducts. Unlike structural generators (e.g., LDBC SNB, Kronecker/R-MAT) or purely LLM-based approaches, SAGA achieves structural realism, semantic richness, and automatic anomaly labeling in a unified framework. On a single H100 GPU with vLLM batching, SAGA generates 500,000 temporal edges with controlled anomalies in under 90 minutes, scaling to 100,000 nodes while maintaining clustering coefficients above 0.99. The system supports real-time pipeline visualization, interactive multi-domain tuning (Finance/AML, Network/IDS, Cyber/APT, Transportation), and a CLI for large-scale GPU-based experiments.

Related papers

• LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals [50.157719466558696]
  We show that modern generators exhibit low-rank collapse in the semantic-residual subspace while preserving the dominant semantic direction.<n>We propose textbfLoRC, a framework that decouples semantic dominance to capture the collapsed residual geometry.<n>Our method improves accuracy by an average of 7.0% across multiple benchmarks and achieves 97.0% accuracy on 39 unseen generators.
  arXiv  Detail & Related papers  (2026-08-21T08:58:47Z)
• When GNNs Fail: Quantifying and Overcoming Temporal Correlation Volatility in Time Series [14.456983509027195]
  We propose Graph Layer for Inference in Dynamic En- vironments (GLIDE), a novel GNN layer enhanced by two theoretically grounded design mechanisms.<n>Experiments on synthetic and real-world benchmarks show that GLIDE improves average performance by up to 45.6% across static and dynamic settings.
  arXiv  Detail & Related papers  (2026-08-07T15:28:45Z)
• Temporal Sheaf Neural Networks with Dynamic Orthogonal Transport [0.5709546417287261]
  We introduce Temporal Sheaf Neural Networks (TSNN), a temporal link prediction framework.<n>TSNN models node-specific and evolving interaction semantics through dynamic local frames.<n>All computations are strictly causal and use only the pre-event history.
  arXiv  Detail & Related papers  (2026-06-08T18:47:31Z)
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning [50.40400074353263]
  Graph Neural Networks (GNNs) are powerful tools for precessing relational data but often struggle to generalize to unseen graphs.<n>We introduce textbfGraph textbfIn-context textbfL textbfTransformer (GILT), a framework built on an LLM-free and tuning-free architecture.
  arXiv  Detail & Related papers  (2025-10-06T08:09:15Z)
• Graph Variate Neural Networks [9.744098349911168]
  We introduce Graph-Variate Neural Networks (GVNNs): layers convolve-temporal signals with a signal-driven connectivity tensor.<n>GVNNs consistently outperform prominent graph-based motor baselines and are competitive with sequence models such as LSTMs and Transformers.<n>On EEG-imagery classification, GVNNs achieve strong accuracy highlighting their potential for brain-computer interface applications.
  arXiv  Detail & Related papers  (2025-09-24T16:44:08Z)
• Taming the Chaos: Coordinated Autoscaling for Heterogeneous and Disaggregated LLM Inference [5.786961198115219]
  Serving Large Language Models (LLMs) is a GPU-intensive task where traditional autoscalers fall short.<n>We introduce HeteroScale, a coordinated autoscaling framework that addresses the core challenges of P/D disaggregated serving.
  arXiv  Detail & Related papers  (2025-08-27T04:22:02Z)
• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization [13.021238902084647]
  Over-smoothing in Graph Neural Networks (GNNs) causes collapse in distinct node features.<n>We introduce SGPC (Sheaf GNNs with PAC-Bayes), a unified architecture that combines cellular-sheaf message passing with several mechanisms.<n> Experiments on nine homophilic and heterophilic benchmarks show that SGPC outperforms state-of-the-art spectral and sheaf-based GNNs.
  arXiv  Detail & Related papers  (2025-08-01T06:39:28Z)
• 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)
• LLM-Based Multi-Agent Systems are Scalable Graph Generative Models [73.28294528654885]
  GraphAgent-Generator (GAG) is a novel simulation-based framework for dynamic, text-attributed social graph generation.<n>GAG simulates the temporal node and edge generation processes for zero-shot social graph generation.<n>The resulting graphs exhibit adherence to seven key macroscopic network properties, achieving an 11% improvement in microscopic graph structure metrics.
  arXiv  Detail & Related papers  (2024-10-13T12:57:08Z)
• Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality [39.476378833827184]
  Anomaly detection in dynamic graphs presents a significant challenge due to the temporal evolution of graph structures and attributes. We introduce a novel spatial- temporal memories-enhanced graph autoencoder (STRIPE) STRIPE significantly outperforms existing methods with 5.8% improvement in AUC scores and 4.62X faster in training time.
  arXiv  Detail & Related papers  (2024-03-14T02:26:10Z)
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation [67.26422477327179]
  Temporal graphs exhibit dynamic interactions between nodes over continuous time. We propose a novel method of temporal graph convolution with the whole neighborhood. Our proposed TAP-GNN outperforms existing temporal graph methods by a large margin in terms of both predictive performance and online inference latency.
  arXiv  Detail & Related papers  (2023-04-15T08:17:18Z)
• Space-Time Graph Neural Networks [104.55175325870195]
  We introduce space-time graph neural network (ST-GNN) to jointly process the underlying space-time topology of time-varying network data. Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs.
  arXiv  Detail & Related papers  (2021-10-06T16:08:44Z)
• GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation [11.526912398475513]
  We propose the Graph Temporal Edge Aggregation framework for inductive learning on Temporal Interaction Graphs (TIGs) By aggregating features of neighboring nodes and the corresponding edge embeddings, GTEA jointly learns both topological and temporal dependencies of a TIG. In addition, a sparsity-inducing self-attention scheme is incorporated for neighbor aggregation, which highlights more important neighbors and suppresses trivial noises for GTEA.
  arXiv  Detail & Related papers  (2020-09-11T07:52:05Z)

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.