mlsanityData to 14 Oct 2026

TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphs

arXiv 2502.19512 ↗First posted 26 Feb 2025cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Fully inductive knowledge graph models can be trained on multiple domains and subsequently perform zero-shot knowledge graph completion (KGC) in new unseen domains. This is an important capability towards the goal of having foundation models for knowledge graphs. In this work, we introduce a more expressive and capable fully inductive model, dubbed TRIX, which not only yields strictly more expressive triplet embeddings (head entity, relation, tail entity) compared to state-of-the-art methods, but also introduces a new capability: directly handling both entity and relation prediction tasks in inductive settings. Empirically, we show that TRIX outperforms the state-of-the-art fully inductive models in zero-shot entity and relation predictions in new domains, and outperforms large-context LLMs in out-of-domain predictions. The source code is available at https://github.com/yuchengz99/TRIX.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 41 of its 57 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

41 of 57 references.

References · 41

  1. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,224
  2. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  5. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  6. 2017Convolutional 2D Knowledge Graph Embeddingscited by 730
  7. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  8. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  9. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 275
  10. 2017DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoningcited by 266
  11. 2019Inductive Relation Prediction by Subgraph Reasoningcited by 239
  12. 2023ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understandingcited by 176
29 more
  1. 2019DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphscited by 175
  2. 2021Equivariant Subgraph Aggregation Networkscited by 154
  3. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
  4. 2023Rethinking the Expressive Power of GNNs via Graph Biconnectivitycited by 119
  5. 2020RNNLogic: Learning Logic Rules for Reasoning on Knowledge Graphscited by 118
  6. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  7. 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
  8. 2020On Learning Sets of Symmetric Elementscited by 98
  9. 2023Towards Foundation Models for Knowledge Graph Reasoningcited by 86
  10. 2022Graph Neural Networks for Link Prediction with Subgraph Sketchingcited by 81
  11. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  12. 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 52
  13. 2023Making Large Language Models Perform Better in Knowledge Graph Completioncited by 48
  14. 2023Exploring Large Language Models for Knowledge Graph Completioncited by 43
  15. 2023Equivariant Polynomials for Graph Neural Networkscited by 38
  16. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  17. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  18. 2024KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completioncited by 36
  19. 2024In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Misscited by 36
  20. 2024Knowledge Graph Large Language Model (KG-LLM) for Link Predictioncited by 36
  21. 2023Dipping PLMs Sauce: Bridging Structure and Text for Effective Knowledge Graph Completion via Conditional Soft Promptingcited by 33
  22. 2022Weisfeiler and Leman Go Relationalcited by 28
  23. 2020Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graphcited by 26
  24. 2022An Open Challenge for Inductive Link Prediction on Knowledge Graphscited by 26
  25. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 24
  26. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  27. 2024Multi-perspective Improvement of Knowledge Graph Completion with Large Language Modelscited by 20
  28. 2020Type-augmented Relation Prediction in Knowledge Graphscited by 12
  29. 2023Anchoring Path for Inductive Relation Prediction in Knowledge Graphscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 15.

24 papers.

Sort:

By area:

  1. 2025Equivariance Everywhere All At Once: A Recipe for Graph Foundation Modelscited by 17
  2. 2025Flock: A Knowledge Graph Foundation Model via Learning on Random Walkscited by 9
  3. 2025SEMMA: A Semantic Aware Knowledge Graph Foundation Modelcited by 8
  4. 2025GraphOracle: Efficient Fully-Inductive Knowledge Graph Reasoning via Relation-Dependency Graphscited by 7
  5. 2025HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphscited by 7
  6. 2026Bridging Input Feature Spaces Towards Graph Foundation Modelscited by 3
  7. 2026RelAgent: LLM Agents as Data Scientists for Relational Learningcited by 2
  8. 2026KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learningcited by 2
  9. 2025Designing a reliable lateral movement detector using a graph foundation modelcited by 1
  10. 2025Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoningcited by 1
  11. 2025Geometric Structural Knowledge Graph Foundation Modelcited by 1
  12. 2026Breaking the Reasoning Horizon in Entity Alignment Foundation Modelscited by 1
12 more
  1. 2026Graphlets as Building Blocks for Structural Vocabulary in Knowledge Graph Foundation Modelscited by 1
  2. 2026Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Modelscited by 1
  3. 2025KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answeringcited by 0
  4. 2026Boosting Knowledge Graph Foundation Models via Enhanced Negative Samplingcited by 0
  5. 2026Harnessing Structural Context for Entity Alignment Foundation Modelscited by 0
  6. 2026GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attentioncited by 0
  7. 2026Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networkscited by 0
  8. 2026FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphscited by 0
  9. 2026Structure-Internalized Rule Language Model for Faithful Knowledge Graph Reasoningcited by 0
  10. 2026Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNscited by 0
  11. 2026The Universal Classifier for Graph Learningcited by 0
  12. 2026MERIT: Scaling KG Foundation Models with Relation Transformerscited by 0