Autoregressive Models for Knowledge Graph Generation

• URL: http://arxiv.org/abs/2602.06707v1
• Date: Fri, 06 Feb 2026 13:50:22 GMT
• Title: Autoregressive Models for Knowledge Graph Generation
• Authors: Thiviyan Thanapalasingam, Antonis Vozikis, Peter Bloem, Paul Groth,
• Abstract summary: Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples.<n>We present ARK, a family of autoregressive models that generate KGs by treating graphs as sequences of (head, relation, tail) triples.<n>ARK learns implicit semantic constraints directly from data, including type consistency, temporal validity, and relational patterns, without explicit rule supervision.
• Score: 2.2999148299770047
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge Graph (KG) generation requires models to learn complex semantic dependencies between triples while maintaining domain validity constraints. Unlike link prediction, which scores triples independently, generative models must capture interdependencies across entire subgraphs to produce semantically coherent structures. We present ARK (Auto-Regressive Knowledge Graph Generation), a family of autoregressive models that generate KGs by treating graphs as sequences of (head, relation, tail) triples. ARK learns implicit semantic constraints directly from data, including type consistency, temporal validity, and relational patterns, without explicit rule supervision. On the IntelliGraphs benchmark, our models achieve 89.2% to 100.0% semantic validity across diverse datasets while generating novel graphs not seen during training. We also introduce SAIL, a variational extension of ARK that enables controlled generation through learned latent representations, supporting both unconditional sampling and conditional completion from partial graphs. Our analysis reveals that model capacity (hidden dimensionality >= 64) is more critical than architectural depth for KG generation, with recurrent architectures achieving comparable validity to transformer-based alternatives while offering substantial computational efficiency. These results demonstrate that autoregressive models provide an effective framework for KG generation, with practical applications in knowledge base completion and query answering.

Related papers

• SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D [51.32219731589742]
  3D scene graphs provide a structured representation of object entities and their relationships.<n>Existing approaches for 3D scene graph generation typically combine scene reconstruction with graph neural networks (GNNs)<n>In this work, we introduce a Scene Graph Retrieval-Reasoning Model in 3D (SGR3 Model)
  arXiv  Detail & Related papers  (2026-03-04T21:19:54Z)
• DyGnROLE: Modeling Asymmetry in Dynamic Graphs with Node-Role-Oriented Latent Encoding [9.701178273182691]
  Real-world dynamic graphs are often directed, with source and destination nodes exhibiting asymmetrical behavioral patterns and temporal dynamics.<n>We propose DyGnROLE, a transformer-based architecture that explicitly disentangles source and destination representations.<n>By using separate embedding vocabularies and role-semantic positional encodings, the model captures the distinct structural and temporal contexts unique to each role.
  arXiv  Detail & Related papers  (2026-02-26T15:51:51Z)
• OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection [48.77471686671269]
  OWLEYE is a novel framework that learns transferable patterns of normal behavior from multiple graphs.<n>We show that OWLEYE achieves superior performance and generalizability compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-01-27T02:08:18Z)
• Continuous Visual Autoregressive Generation via Score Maximization [69.67438563485887]
  We introduce a Continuous VAR framework that enables direct visual autoregressive generation without vector quantization.<n>Within this framework, all we need is to select a strictly proper score and set it as the training objective to optimize.
  arXiv  Detail & Related papers  (2025-05-12T17:58:14Z)
• Efficient Relational Context Perception for Knowledge Graph Completion [25.903926643251076]
  Knowledge Graphs (KGs) provide a structured representation of knowledge but often suffer from challenges of incompleteness.<n>Previous knowledge graph embedding models are limited in their ability to capture expressive features.<n>We propose Triple Receptance Perception architecture to model sequential information, enabling the learning of dynamic context.
  arXiv  Detail & Related papers  (2024-12-31T11:25:58Z)
• A Contextualized BERT model for Knowledge Graph Completion [0.0]
  We introduce a contextualized BERT model for Knowledge Graph Completion (KGC)<n>Our model eliminates the need for entity descriptions and negative triplet sampling, reducing computational demands while improving performance.<n>Our model outperforms state-of-the-art methods on standard datasets, improving Hit@1 by 5.3% and 4.88% on FB15k-237 and WN18RR respectively.
  arXiv  Detail & Related papers  (2024-12-15T02:03:16Z)
• Deep Sparse Latent Feature Models for Knowledge Graph Completion [24.342670268545085]
  This paper presents a novel probabilistic KGC framework utilizing sparse latent feature models, optimized via a deep variational autoencoder (VAE)<n>Our proposed method dynamically global clustering information with local textual features to effectively complete missing triples, while also providing enhanced interpretability of the underlying latent structures.
  arXiv  Detail & Related papers  (2024-11-24T03:17:37Z)
• On the Role of Edge Dependency in Graph Generative Models [28.203109773986167]
  We introduce a novel evaluation framework for generative models of graphs. We focus on the importance of model-generated graph overlap to ensure both accuracy and edge-diversity. Our results indicate that our simple, interpretable models provide competitive baselines to popular generative models.
  arXiv  Detail & Related papers  (2023-12-06T18:54:27Z)
• KGLM: Integrating Knowledge Graph Structure in Language Models for Link Prediction [0.0]
  We introduce a new entity/relation embedding layer that learns to differentiate distinctive entity and relation types. We show that further pre-training the language models with this additional embedding layer using the triples extracted from the knowledge graph, followed by the standard fine-tuning phase sets a new state-of-the-art performance for the link prediction task on the benchmark datasets.
  arXiv  Detail & Related papers  (2022-11-04T20:38:12Z)
• ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion [78.8942067357231]
  ExpressivE embeds pairs of entities as points and relations as hyper-parallelograms in the virtual triple space. We show that ExpressivE is competitive with state-of-the-art KGEs and even significantly outperforms them on W18RR.
  arXiv  Detail & Related papers  (2022-06-08T23:34:39Z)
• Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic Cones [64.75766944882389]
  We present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph. In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies. Our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR)
  arXiv  Detail & Related papers  (2021-10-28T07:16:08Z)
• Learning Intents behind Interactions with Knowledge Graph for Recommendation [93.08709357435991]
  Knowledge graph (KG) plays an increasingly important role in recommender systems. Existing GNN-based models fail to identify user-item relation at a fine-grained level of intents. We propose a new model, Knowledge Graph-based Intent Network (KGIN)
  arXiv  Detail & Related papers  (2021-02-14T03:21:36Z)
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning [74.05478502080658]
  This paper introduces a tensor-graph convolutional network (TGCN) for scalable semi-supervised learning (SSL) from data associated with a collection of graphs, that are represented by a tensor. The proposed architecture achieves markedly improved performance relative to standard GCNs, copes with state-of-the-art adversarial attacks, and leads to remarkable SSL performance over protein-to-protein interaction networks.
  arXiv  Detail & Related papers  (2020-03-15T02:33:21Z)

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.