Bi-View Embedding Fusion: A Hybrid Learning Approach for Knowledge Graph's Nodes Classification Addressing Problems with Limited Data

2025-11-17

AI Summary

To address performance bottlenecks in knowledge graph (KG) node classification under label sparsity and impoverished initial node features, this paper proposes a dual-view embedding fusion framework. The method jointly models structural and semantic information: (i) unsupervised topological representation via Node2Vec augmented with centrality measures; and (ii) supervised neighborhood-aware semantic aggregation using GraphSAGE. A learnable fusion layer aligns and integrates these complementary embeddings without requiring synthetic data, thereby uncovering latent discriminative features. Experiments demonstrate significant improvements in node classification accuracy under sparse labeling regimes, alongside enhanced model robustness and generalization. The approach establishes an efficient, lightweight, and interpretable paradigm for KG-enhanced graph learning.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Traditional Machine Learning (ML) methods require large amounts of data to perform well, limiting their applicability in sparse or incomplete scenarios and forcing the usage of additional synthetic data to improve the model training. To overcome this challenge, the research community is looking more and more at Graph Machine Learning (GML) as it offers a powerful alternative by using relationships within data. However, this method also faces limitations, particularly when dealing with Knowledge Graphs (KGs), which can hide huge information due to their semantic nature. This study introduces Bi-View, a novel hybrid approach that increases the informative content of node features in KGs to generate enhanced Graph Embeddings (GEs) that are used to improve GML models without relying on additional synthetic data. The proposed work combines two complementary GE techniques: Node2Vec, which captures structural patterns through unsupervised random walks, and GraphSAGE, which aggregates neighbourhood information in a supervised way. Node2Vec embeddings are first computed to represent the graph topology, and node features are then enriched with centrality-based metrics, which are used as input for the GraphSAGE model. Moreover, a fusion layer combines the original Node2Vec embeddings with the GraphSAGE-influenced representations, resulting in a dual-perspective embedding space. Such a fusion captures both topological and semantic properties of the graph, enabling the model to exploit informative features that may exist in the dataset but that are not explicitly represented. Our approach improves downstream task performance, especially in scenarios with poor initial features, giving the basis for more accurate and precise KG-enanched GML models.

Problem

• Overcoming limited data challenges in knowledge graph node classification
• Enhancing graph embeddings by fusing topological and semantic properties
• Improving graph machine learning models without synthetic data

Innovation

• Hybrid fusion of Node2Vec and GraphSAGE embeddings
• Enriches node features with centrality-based metrics
• Combines topological and semantic graph properties