mlsanityData to 7 Oct 2026

NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training

arXiv 2602.21597 ↗First posted 25 Feb 2026cs.LGcited by 2

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-exclusive embeddings. We present NGDB-Zoo, a unified framework that resolves these bottlenecks by synergizing operator-level training with semantic augmentation. By decoupling logical operators from query topologies, NGDB-Zoo transforms the training loop into a dynamically scheduled data-flow execution, enabling multi-stream parallelism and achieving a 1.8× - 6.8× throughput compared to baselines. Furthermore, we formalize a decoupled architecture to integrate high-dimensional semantic priors from Pre-trained Text Encoders (PTEs) without triggering I/O stalls or memory overflows. Extensive evaluations on six benchmarks, including massive graphs like ogbl-wikikg2 and ATLAS-Wiki, demonstrate that NGDB-Zoo maintains high GPU utilization across diverse logical patterns and significantly mitigates representation friction in hybrid neuro-symbolic reasoning.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 54 of its 63 references that are in the map. First posted on arXiv 25 Feb 2026.

Builds on

54 of 63 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Neural Graph Reasoning: Complex Logical Query Answering Meets Graph Databases26 Mar
  2. 2022GammaE: Gamma Embeddings for Logical Queries on Knowledge Graphs27 Oct

Other references · 52

  1. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  2. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  3. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
  5. 2014Embedding Entities and Relations for Learning and Inference in Knowledge Basescited by 929
  6. 2016Complex Embeddings for Simple Link Predictioncited by 897
  7. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 893
  8. 2020Heterogeneous Graph Transformercited by 581
  9. 2019Graph Transformer Networkscited by 520
  10. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 409
  11. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  12. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 323
38 more
  1. 2022Structure-Aware Transformer for Graph Representation Learningcited by 191
  2. 2022Pure Transformers are Powerful Graph Learnerscited by 188
  3. 2020Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddingscited by 169
  4. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 128
  5. 2018Embedding Logical Queries on Knowledge Graphscited by 120
  6. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 118
  7. 2021TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learningcited by 116
  8. 2022Transformer for Graphs: An Overview from Architecture Perspectivecited by 107
  9. 2022SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Modelscited by 90
  10. 2020Message Passing for Hyper-Relational Knowledge Graphscited by 78
  11. 2020DGL-KE: Training Knowledge Graph Embeddings at Scalecited by 67
  12. 2025Griffin: Towards a Graph-Centric Relational Database Foundation Modelcited by 41
  13. 2020Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphscited by 35
  14. 2021Marius: Learning Massive Graph Embeddings on a Single Machinecited by 29
  15. 2022Query2Particles: Knowledge Graph Reasoning with Particle Embeddingscited by 24
  16. 2025AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corporacited by 23
  17. 2024Discrete Diffusion Schr"odinger Bridge Matching for Graph Transformationcited by 21
  18. 2024PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemscited by 18
  19. 2021SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphscited by 17
  20. 2025Graph World Modelcited by 14
  21. 2021FastSeq: Make Sequence Generation Fastercited by 13
  22. 2023Sequential Query Encoding For Complex Query Answering on Knowledge Graphscited by 13
  23. 2024A Foundation Model for Zero-shot Logical Query Reasoningcited by 13
  24. 2025Top Ten Challenges Towards Agentic Neural Graph Databasescited by 13
  25. 2025Flatten Graphs as Sequences: Transformers are Scalable Graph Generatorscited by 12
  26. 2022Neural Graph Databasescited by 11
  27. 2023Knowledge Graph Embedding: An Overviewcited by 10
  28. 2023DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimizationcited by 9
  29. 2023Geometric Relational Embeddings: A Surveycited by 8
  30. 2025Joint Relational Database Generation via Graph-Conditional Diffusion Modelscited by 8
  31. 2025RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databasescited by 8
  32. 2024Training-Free Message Passing for Learning on Hypergraphscited by 7
  33. 2025Improving the Effective Receptive Field of Message-Passing Neural Networkscited by 6
  34. 2023Privacy-Preserved Neural Graph Databasescited by 5
  35. 2023Query2GMM: Learning Representation with Gaussian Mixture Model for Reasoning over Knowledge Graphscited by 4
  36. 2024Pushing the Limits of All-Atom Geometric Graph Neural Networks: Pre-Training, Scaling and Zero-Shot Transfercited by 3
  37. 2025Accurate and Scalable Graph Neural Networks via Message Invariancecited by 3
  38. 2025A Few Moments Please: Scalable Graphon Learning via Moment Matchingcited by 3

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learningcited by 2
  2. 2026HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Neural Methods for Logical Reasoning Over Knowledge Graphs
  2. 2022Inductive Logical Query Answering in Knowledge Graphs
  3. 2024A Context-Enhanced Framework for Sequential Graph Reasoning
  4. 2025A Large Language Model Based Method for Complex Logical Reasoning over Knowledge Graphs
  5. 2024GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
  6. 2025Encoder-Free Knowledge-Graph Reasoning with LLMs via Hyperdimensional Path Retrieval
  7. 2025DeepGraphLog for Layered Neurosymbolic AI
  8. 2026GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs