Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings

• URL: http://arxiv.org/abs/2606.29180v2
• Date: Tue, 30 Jun 2026 04:10:55 GMT
• Title: Measuring Graph-to-Graph Semantic Similarity in Knowledge Graphs: An Empirical Evaluation of Knowledge Graph Embeddings
• Abstract summary: A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains.<n>Existing embedding methods mainly focus on entities, relations, and triples, leaving graph-level semantics largely unaddressed.<n>Conventional graph-level methods, which typically compare graphs based on structural patterns, are also insufficient because structural similarity alone cannot guarantee semantic similarity between KGs.
• Score: 7.760140208674582
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: A Knowledge Graph (KG) represents facts as structured triples and is widely used to organize relational knowledge across diverse domains. Just as textual information ranges from words and sentences to complete documents, KG information can be interpreted at multiple levels, from entities, relations, and triples to subgraphs and entire KGs. However, existing KG embedding methods mainly focus on entities, relations, and triples, leaving graph-level semantics largely unaddressed. Conventional graph-level methods, which typically compare graphs based on structural patterns, are also insufficient because structural similarity alone cannot guarantee semantic similarity between KGs. To evaluate how well different methods capture such graph-level semantic information, we study graph-to-graph semantic similarity, which determines whether a pair of KGs represents semantically corresponding underlying information. To obtain reliable ground-truth correspondences, we construct a semantic matching dataset by modifying text documents, extracting KGs from both original and modified documents, and transferring their known correspondences to KG pairs. We compare text-based, structure-based, and KG embedding-based approaches on each dataset. For the KG embedding-based approach, we introduce two scoring functions: \textit{EmbPairSim}, which uses maximal pairwise entity similarity, and \textit{AvgEmbSim}, which uses a frequency-weighted centroid. Experiments on WikiText-2 and CC-News show that \textit{EmbPairSim} achieves up to 5.3 pp higher MRR than Sentence-BERT while using substantially fewer parameters. These results suggest that KGE representations can serve as compact and effective signals for graph-to-graph semantic similarity in KGs. Our code is available at https://github.com/SeungRyeolBaek/KG-to-KG-Semantic-Similarity.

Related papers

• KGCQual: An Interpretable Framework for Evaluating the Knowledge Graph Construction Quality from Text [6.373904244962351]
  We propose a novel, interpretable metric for intrinsic Knowledge Graph quality assessment.<n>It measures how closely an automatically extracted graph approximates an "ideal" graph.<n>We evaluate our metric across multiple state-of-the-art triple extraction systems and datasets.
  arXiv  Detail & Related papers  (2026-07-11T08:45:15Z)
• KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning [51.44698654440413]
  Knowledge graph (KG) foundation models aim to generalize across graphs with unseen entities and relations by learning transferable relational structure.<n>We propose KGPFN, a KG foundation model that unifies transferable relational regularities with inference-time in-context learning.<n>Experiments on 57 KG benchmarks demonstrate that KGPFN achieves strong adaptation to previously unseen graphs through in-context learning alone.
  arXiv  Detail & Related papers  (2026-05-14T14:41:19Z)
• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models [16.2387767061355]
  KG-BiLM is a bidirectional LM framework that fuses structural cues from KGs with the semantic expressiveness of generative transformers.<n> KG-BiLM incorporates three key components: (i) Bidirectional Knowledge Attention, which removes the causal mask to enable full interaction among all tokens and entities; (ii) Knowledge-Masked Prediction, which encourages the model to leverage both local semantic contexts and global graph connectivity; and (iii) Contrastive Graph Semantic Aggregation, which preserves KG structure via contrastive alignment of sampled sub-graph representations.
  arXiv  Detail & Related papers  (2025-06-04T04:47:24Z)
• Relation Extraction Across Entire Books to Reconstruct Community Networks: The AffilKG Datasets [3.9244082434642555]
  AffilKG is a collection of six datasets that are the first to pair complete book scans with large, labeled knowledge graphs.<n>Each dataset features affiliation graphs, which are simple KGs that capture Member relationships between Person and Organization entities.
  arXiv  Detail & Related papers  (2025-05-16T02:24:32Z)
• EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completion [54.12709176438264]
  Commonsense knowledge graphs (CSKGs) utilize free-form text to represent named entities, short phrases, and events as their nodes. Current methods leverage semantic similarities to increase the graph density, but the semantic plausibility of the nodes and their relations are under-explored. We propose to adopt textual entailment to find implicit entailment relations between CSKG nodes, to effectively densify the subgraph connecting nodes within the same conceptual class.
  arXiv  Detail & Related papers  (2024-02-15T02:27:23Z)
• Universal Preprocessing Operators for Embedding Knowledge Graphs with Literals [2.211868306499727]
  Knowledge graph embeddings are dense numerical representations of entities in a knowledge graph (KG) We propose a set of universal preprocessing operators which can be used to transform KGs with literals for numerical, temporal, textual, and image information. The results on the kgbench dataset with three different embedding methods show promising results.
  arXiv  Detail & Related papers  (2023-09-06T14:08:46Z)
• Text-To-KG Alignment: Comparing Current Methods on Classification Tasks [2.191505742658975]
  knowledge graphs (KG) provide dense and structured representations of factual information. Recent work has focused on creating pipeline models that retrieve information from KGs as additional context. It is not known how current methods compare to a scenario where the aligned subgraph is completely relevant to the query.
  arXiv  Detail & Related papers  (2023-06-05T13:45:45Z)
• 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)
• FactGraph: Evaluating Factuality in Summarization with Semantic Graph Representations [114.94628499698096]
  We propose FactGraph, a method that decomposes the document and the summary into structured meaning representations (MRs) MRs describe core semantic concepts and their relations, aggregating the main content in both document and summary in a canonical form, and reducing data sparsity. Experiments on different benchmarks for evaluating factuality show that FactGraph outperforms previous approaches by up to 15%.
  arXiv  Detail & Related papers  (2022-04-13T16:45:33Z)
• FedE: Embedding Knowledge Graphs in Federated Setting [21.022513922373207]
  Multi-Source KG is a common situation in real Knowledge Graph applications. Because of the data privacy and sensitivity, a set of relevant knowledge graphs cannot complement each other's KGC by just collecting data from different knowledge graphs together. We propose a Federated Knowledge Graph Embedding framework FedE, focusing on learning knowledge graph embeddings by aggregating locally-computed updates.
  arXiv  Detail & Related papers  (2020-10-24T11:52:05Z)
• Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion [53.31911669146451]
  Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks. These graphs are usually incomplete, urging auto-completion of them. graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements into dense embeddings. textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations.
  arXiv  Detail & Related papers  (2020-04-30T13:50:34Z)
• On the Role of Conceptualization in Commonsense Knowledge Graph Construction [59.39512925793171]
  Commonsense knowledge graphs (CKGs) like Atomic and ASER are substantially different from conventional KGs. We introduce to CKG construction methods conceptualization to view entities mentioned in text as instances of specific concepts or vice versa. Our methods can effectively identify plausible triples and expand the KG by triples of both new nodes and edges of high diversity and novelty.
  arXiv  Detail & Related papers  (2020-03-06T14:35:20Z)

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.