Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing

• URL: http://arxiv.org/abs/2506.23141v1
• Date: Sun, 29 Jun 2025 08:37:48 GMT
• Title: Context-Driven Knowledge Graph Completion with Semantic-Aware Relational Message Passing
• Authors: Siyuan Li, Ruitong Liu, Yan Wen, Te Sun,
• Abstract summary: Semantic context surrounding a triplet $(h, r, t)$ is crucial for Knowledge Graph Completion (KGC)<n>Traditional node-based message passing mechanisms often introduce noise and suffer from information dilution or over-smoothing.<n>We propose a semantic-aware relational message passing framework.
• Score: 18.480268023065747
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Semantic context surrounding a triplet $(h, r, t)$ is crucial for Knowledge Graph Completion (KGC), providing vital cues for prediction. However, traditional node-based message passing mechanisms, when applied to knowledge graphs, often introduce noise and suffer from information dilution or over-smoothing by indiscriminately aggregating information from all neighboring edges. To address this challenge, we propose a semantic-aware relational message passing. A core innovation of this framework is the introduction of a \textbf{semantic-aware Top-K neighbor selection strategy}. Specifically, this strategy first evaluates the semantic relevance between a central node and its incident edges within a shared latent space, selecting only the Top-K most pertinent ones. Subsequently, information from these selected edges is effectively fused with the central node's own representation using a \textbf{multi-head attention aggregator} to generate a semantically focused node message. In this manner, our model not only leverages the structure and features of edges within the knowledge graph but also more accurately captures and propagates the contextual information most relevant to the specific link prediction task, thereby effectively mitigating interference from irrelevant information. Extensive experiments demonstrate that our method achieves superior performance compared to existing approaches on several established benchmarks.

Related papers

• Knowledge Graph Completion with Relation-Aware Anchor Enhancement [50.50944396454757]
  We propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC)<n>We first generate anchor entities within the relation-aware neighborhood of the head entity.<n>Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching.
  arXiv  Detail & Related papers  (2025-04-08T15:22:08Z)
• Semantic Communication Enhanced by Knowledge Graph Representation Learning [11.68356846628016]
  This paper investigates the advantages of representing and processing semantic knowledge extracted into graphs within the emerging paradigm of semantic communications. We propose sending semantic symbols solely equivalent to node embeddings through the wireless channel and inferring the complete knowledge graph at the receiver.
  arXiv  Detail & Related papers  (2024-07-27T20:57:10Z)
• Multi-Evidence based Fact Verification via A Confidential Graph Neural Network [20.574234947055494]
  We introduce a Confidential Graph Attention Network (CO-GAT) to mitigate the propagation of noisy semantic information. CO-GAT achieves a 73.59% FEVER score on the FEVER dataset and shows the ability generalization by broadening the effectiveness.
  arXiv  Detail & Related papers  (2024-05-17T01:02:03Z)
• Unified Lattice Graph Fusion for Chinese Named Entity Recognition [9.863877505377165]
  We propose a Unified Lattice Graph Fusion (ULGF) approach for Chinese named entity recognition. We stack multiple graph-based intra-source self-attention and inter-source cross-gating fusion layers that iteratively carry out semantic interactions to learn node representations.
  arXiv  Detail & Related papers  (2023-12-28T09:31:25Z)
• KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification [75.95647590619929]
  Zero-Shot Node Classification (ZNC) has been an emerging and crucial task in graph data analysis. We propose a Knowledge-Aware Multi-Faceted framework (KMF) that enhances the richness of label semantics. A novel geometric constraint is developed to alleviate the problem of prototype drift caused by node information aggregation.
  arXiv  Detail & Related papers  (2023-08-15T02:38:08Z)
• Performance Optimization for Semantic Communications: An Attention-based Reinforcement Learning Approach [187.4094332217186]
  A semantic communication framework is proposed for textual data transmission. A metric of semantic similarity (MSS) that jointly captures the semantic accuracy and completeness of the recovered text is proposed.
  arXiv  Detail & Related papers  (2022-08-17T11:39:16Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Towards Efficient Scene Understanding via Squeeze Reasoning [71.1139549949694]
  We propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks.
  arXiv  Detail & Related papers  (2020-11-06T12:17:01Z)
• Self-Supervised Learning of Contextual Embeddings for Link Prediction in Heterogeneous Networks [11.540329725077843]
  We develop SLiCE, a framework bridging static representation learning methods using global information from the entire graph. We first pre-train our model in a self-supervised manner by introducing higher-order semantic associations and masking nodes. We also interpret the semantic association matrix and provide its utility and relevance in making successful link predictions between heterogeneous nodes in the network.
  arXiv  Detail & Related papers  (2020-07-22T03:48:53Z)
• ORD: Object Relationship Discovery for Visual Dialogue Generation [60.471670447176656]
  We propose an object relationship discovery (ORD) framework to preserve the object interactions for visual dialogue generation. A hierarchical graph convolutional network (HierGCN) is proposed to retain the object nodes and neighbour relationships locally, and then refines the object-object connections globally. Experiments have proved that the proposed method can significantly improve the quality of dialogue by utilising the contextual information of visual relationships.
  arXiv  Detail & Related papers  (2020-06-15T12:25:40Z)

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.