Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment
Preprint
Abstract
In Multi-Modal Knowledge Graphs (MMKGs), Multi-Modal Entity Alignment (MMEA) is crucial for identifying identical entities across diverse modal attributes. However, semantic inconsistency, mainly due to missing modal attributes, poses a significant challenge. Traditional approaches rely on attribute interpolation, but this often introduces modality noise, distorting the original semantics. Moreover, the lack of a universal theoretical framework limits advancements in achieving semantic consistency. This study introduces a novel approach, DESAlign, which addresses these issues by applying a theoretical framework based on Dirichlet energy to ensure semantic consistency. We discover that semantic inconsistency leads to model overfitting to modality noise, causing performance fluctuations, particularly when modalities are missing. DESAlign innovatively combats over-smoothing and interpolates absent semantics using existing modalities. Our approach includes a multi-modal knowledge graph learning strategy and a propagation technique that employs existing semantic features to compensate for missing ones, providing explicit Euler solutions. Comprehensive evaluations across 18 benchmarks, including monolingual and bilingual scenarios, demonstrate that DESAlign surpasses existing methods, setting a new standard in performance. Further testing on 42 benchmarks with high rates of missing modalities confirms its robustness, offering an effective solution to semantic inconsistency in real-world MMKGs.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment2023
- MEAformer: Multi-modal Entity Alignment Transformer for Meta Modality Hybrid2023
- Multi-Modal Knowledge Graph Construction and Application: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2022
- MultiJAF: Multi-modal joint entity alignment framework for multi-modal knowledge graphNeurocomputing, 2022
- Multi-modal entity alignment in hyperbolic spaceNeurocomputing, 2021
- Entity Alignment for Knowledge Graphs With Multi-Order Convolutional NetworksIEEE Transactions on Knowledge and Data Engineering, 2020
- Emotion recognition using multi-modal data and machine learning techniques: A tutorial and reviewInformation Fusion, 2020
- Neighborhood-Aware Attentional Representation for Multilingual Knowledge Graphs2019
- Bootstrapping Entity Alignment with Knowledge Graph Embedding2018
- Iterative Entity Alignment via Joint Knowledge Embeddings2017