# Multi-modal Entity Alignment in Hyperbolic Space

arXiv: https://arxiv.org/abs/2106.03619 · HTML: https://mlsanity.com/paper/2106.03619/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 46 references that are in the map.
- First posted on arXiv 7 Jun 2021.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [A Survey on Knowledge Graphs: Representation, Acquisition and Applications](https://mlsanity.com/paper/2002.00388/) (2020)
- [Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding](https://mlsanity.com/paper/1810.02338/) (2018)
- [Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry](https://mlsanity.com/paper/1806.03417/) (2018)
- [Deep Convolutional Networks on Graph-Structured Data](https://mlsanity.com/paper/1506.05163/) (2015)
- [Hyperbolic Entailment Cones for Learning Hierarchical Embeddings](https://mlsanity.com/paper/1804.01882/) (2018)
- [Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment](https://mlsanity.com/paper/1611.03954/) (2016)
- [Cross-lingual Entity Alignment via Joint Attribute-Preserving Embedding](https://mlsanity.com/paper/1708.05045/) (2017)
- [Hyperbolic Attention Networks](https://mlsanity.com/paper/1805.09786/) (2018)
- [Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs](https://mlsanity.com/paper/1908.08210/) (2019)
- [MMKG: Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/1903.05485/) (2019)
- [Multi-Channel Graph Neural Network for Entity Alignment](https://mlsanity.com/paper/1908.09898/) (2019)
- [Image-embodied Knowledge Representation Learning](https://mlsanity.com/paper/1609.07028/) (2016)
- [KBQA: Learning Question Answering over QA Corpora and Knowledge Bases](https://mlsanity.com/paper/1903.02419/) (2019)
- [Neighborhood Matching Network for Entity Alignment](https://mlsanity.com/paper/2005.05607/) (2020)
- [Collective Entity Alignment via Adaptive Features](https://mlsanity.com/paper/1912.08404/) (2019)
- [Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space](https://mlsanity.com/paper/1602.06522/) (2016)
- [Dual-Primal Graph Convolutional Networks](https://mlsanity.com/paper/1806.00770/) (2018)
- [Degree-Aware Alignment for Entities in Tail](https://mlsanity.com/paper/2005.12132/) (2020)

## Built on by (most cited first, 19 of 19)

- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [Multi-Modal Knowledge Graph Construction and Application: A Survey](https://mlsanity.com/paper/2202.05786/) (2022)
- [Hyperbolic Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/2305.06611/) (2023)
- [Knowledge Graphs: Opportunities and Challenges](https://mlsanity.com/paper/2303.13948/) (2023)
- [Multi-modal Contrastive Representation Learning for Entity Alignment](https://mlsanity.com/paper/2209.00891/) (2022)
- [SGAligner : 3D Scene Alignment with Scene Graphs](https://mlsanity.com/paper/2304.14880/) (2023)
- [Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2304.01563/) (2023)
- [Multi-Modal Knowledge Graph Transformer Framework for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2310.06365/) (2023)
- [Noise-powered Multi-modal Knowledge Graph Representation Framework](https://mlsanity.com/paper/2403.06832/) (2024)
- [Robust Hyperbolic Learning with Curvature-Aware Optimization](https://mlsanity.com/paper/2405.13979/) (2024)
- [IBMEA: Exploring Variational Information Bottleneck for Multi-modal Entity Alignment](https://mlsanity.com/paper/2407.19302/) (2024)
- [Leveraging Intra-modal and Inter-modal Interaction for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2404.17590/) (2024)
- [LoginMEA: Local-to-Global Interaction Network for Multi-modal Entity Alignment](https://mlsanity.com/paper/2407.19625/) (2024)
- [Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning](https://mlsanity.com/paper/2412.05028/) (2024)
- [Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment](https://mlsanity.com/paper/2510.18240/) (2025)
- [Mitigating Modality Bias in Multi-modal Entity Alignment from a Causal Perspective](https://mlsanity.com/paper/2504.19458/) (2025)
- [Design of the topology for contrastive visual-textual alignment](https://mlsanity.com/paper/2209.02127/) (2022)
- [HCFSLN: Adaptive Hyperbolic Few-Shot Learning for Multimodal Anxiety Detection](https://mlsanity.com/paper/2511.06988/) (2025)
- [Time Imprint: Learning Time-Aware Representations in Multi-Modal Knowledge Graphs](https://mlsanity.com/paper/2607.09777/) (2026)

## Abstract (arXiv)

Many AI-related tasks involve the interactions of data in multiple modalities. It has been a new trend to merge multi-modal information into knowledge graph(KG), resulting in multi-modal knowledge graphs (MMKG). However, MMKGs usually suffer from low coverage and incompleteness. To mitigate this problem, a viable approach is to integrate complementary knowledge from other MMKGs. To this end, although existing entity alignment approaches could be adopted, they operate in the Euclidean space, and the resulting Euclidean entity representations can lead to large distortion of KG's hierarchical structure. Besides, the visual information has yet not been well exploited. In response to these issues, in this work, we propose a novel multi-modal entity alignment approach, Hyperbolic multi-modal entity alignment(HMEA), which extends the Euclidean representation to hyperboloid manifold. We first adopt the Hyperbolic Graph Convolutional Networks (HGCNs) to learn structural representations of entities. Regarding the visual information, we generate image embeddings using the densenet model, which are also projected into the hyperbolic space using HGCNs. Finally, we combine the structure and visual representations in the hyperbolic space and use the aggregated embeddings to predict potential alignment results. Extensive experiments and ablation studies demonstrate the effectiveness of our proposed model and its components.