mlsanityData to 14 Oct 2026

SEMMA: A Semantic Aware Knowledge Graph Foundation Model

arXiv 2505.20422 ↗First posted 26 May 2025cs.CL cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Knowledge Graph Foundation Models (KGFMs) have shown promise in enabling zero-shot reasoning over unseen graphs by learning transferable patterns. However, most existing KGFMs rely solely on graph structure, overlooking the rich semantic signals encoded in textual attributes. We introduce SEMMA, a dual-module KGFM that systematically integrates transferable textual semantics alongside structure. SEMMA leverages Large Language Models (LLMs) to enrich relation identifiers, generating semantic embeddings that subsequently form a textual relation graph, which is fused with the structural component. Across 54 diverse KGs, SEMMA outperforms purely structural baselines like ULTRA in fully inductive link prediction. Crucially, we show that in more challenging generalization settings, where the test-time relation vocabulary is entirely unseen, structural methods collapse while SEMMA is 2x more effective. Our findings demonstrate that textual semantics are critical for generalization in settings where structure alone fails, highlighting the need for foundation models that unify structural and linguistic signals in knowledge reasoning.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 72 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

39 of 72 references.

References · 39

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  3. 2019Language Models as Knowledge Bases?cited by 1,936
  4. 2016Complex Embeddings for Simple Link Predictioncited by 902
  5. 2019RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Spacecited by 898
  6. 2020A Survey on Knowledge Graphs: Representation, Acquisition and Applicationscited by 643
  7. 2020Knowledge Graphscited by 621
  8. 2019KG-BERT: BERT for Knowledge Graph Completioncited by 324
  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. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 149
27 more
  1. 2024jina-embeddings-v3: Multilingual Embeddings With Task LoRAcited by 141
  2. 2020Beta Embeddings for Multi-Hop Logical Reasoning in Knowledge Graphscited by 129
  3. 2020CoDEx: A Comprehensive Knowledge Graph Completion Benchmarkcited by 102
  4. 2024Position: Graph Foundation Models are Already Herecited by 86
  5. 2018End-to-End Neural Entity Linkingcited by 85
  6. 2020Inductive Entity Representations from Text via Link Predictioncited by 62
  7. 2019Commonsense Knowledge Base Completion with Structural and Semantic Contextcited by 61
  8. 2023InGram: Inductive Knowledge Graph Embedding via Relation Graphscited by 52
  9. 2021Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representationscited by 37
  10. 2018Improving Knowledge Graph Embedding Using Simple Constraintscited by 36
  11. 2020Fusing Context Into Knowledge Graph for Commonsense Question Answeringcited by 33
  12. 2024A Survey on Temporal Knowledge Graph: Representation Learning and Applicationscited by 30
  13. 2020Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graphcited by 26
  14. 2022An Open Challenge for Inductive Link Prediction on Knowledge Graphscited by 26
  15. 2023A Multi-Task Perspective for Link Prediction with New Relation Types and Nodescited by 24
  16. 2025TRIX: A More Expressive Model for Zero-shot Domain Transfer in Knowledge Graphscited by 24
  17. 2025How Expressive are Knowledge Graph Foundation Models?cited by 23
  18. 2023Double Equivariance for Inductive Link Prediction for Both New Nodes and New Relation Typescited by 21
  19. 2022Knowledge Graph Question Answering Leaderboard: A Community Resource to Prevent a Replication Crisiscited by 14
  20. 2024A Foundation Model for Zero-shot Logical Query Reasoningcited by 14
  21. 2024LLM as Prompter: Low-resource Inductive Reasoning on Arbitrary Knowledge Graphscited by 13
  22. 2024Is Complex Query Answering Really Complex?cited by 8
  23. 2024Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphscited by 6
  24. 2025Knowledge Graph Completion with Relation-Aware Anchor Enhancementcited by 5
  25. 2024DAGE: DAG Query Answering via Relational Combinator with Logical Constraintscited by 4
  26. 2022Integrating Knowledge Graph embedding and pretrained Language Models in Hypercomplex Spacescited by 2
  27. 2024KG4RecEval: Does Knowledge Graph Really Matter for Recommender Systems?cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2025A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Modelscited by 2
  2. 2026Half a Link can Be Enough to Predict a Whole Link: Understanding Generalization in Knowledge Graph Foundation Modelscited by 1
  3. 2025OpenGloss: A Synthetic Encyclopedic Dictionary and Semantic Knowledge Graphcited by 0
  4. 2026UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAGcited by 0
  5. 2026Boosting Knowledge Graph Foundation Models via Enhanced Negative Samplingcited by 0
  6. 2026Graph Evidence Is Not Enough: Diagnosing Native Decoder Use in Graph-Augmented LLMscited by 0
  7. 2026Reification as a Transferable Vocabulary: Zero-Shot Link Prediction with Vanilla GNNscited by 0
  8. 2026MERIT: Scaling KG Foundation Models with Relation Transformerscited by 0