# FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs

arXiv: https://arxiv.org/abs/2510.00894 · HTML: https://mlsanity.com/paper/2510.00894/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [Complex Embeddings for Simple Link Prediction](https://mlsanity.com/paper/1606.06357/) (2016)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [One-Shot Relational Learning for Knowledge Graphs](https://mlsanity.com/paper/1808.09040/) (2018)
- [Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs](https://mlsanity.com/paper/1909.01515/) (2019)
- [A Re-evaluation of Knowledge Graph Completion Methods](https://mlsanity.com/paper/1911.03903/) (2019)
- [Image-embodied Knowledge Representation Learning](https://mlsanity.com/paper/1609.07028/) (2016)
- [Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/1911.11298/) (2019)
- [Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey](https://mlsanity.com/paper/2402.05391/) (2024)
- [Multimodal Reasoning with Multimodal Knowledge Graph](https://mlsanity.com/paper/2406.02030/) (2024)
- [Adaptive Attentional Network for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2010.09638/) (2020)
- [Modular and Parameter-Efficient Multimodal Fusion with Prompting](https://mlsanity.com/paper/2203.08055/) (2022)
- [Relational Learning with Gated and Attentive Neighbor Aggregator for Few-Shot Knowledge Graph Completion](https://mlsanity.com/paper/2104.13095/) (2021)
- [KBLRN : End-to-End Learning of Knowledge Base Representations with Latent, Relational, and Numerical Features](https://mlsanity.com/paper/1709.04676/) (2017)
- [NativE: Multi-modal Knowledge Graph Completion in the Wild](https://mlsanity.com/paper/2406.17605/) (2024)
- [Context-Aware Adapter Tuning for Few-Shot Relation Learning in Knowledge Graphs](https://mlsanity.com/paper/2410.09123/) (2024)

## Abstract (arXiv)

Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we propose FusionAdapter for the learning of few-shot relationships (FSRL) in MMKG. FusionAdapter introduces (1) an adapter module that enables efficient adaptation of each modality to unseen relations and (2) a fusion strategy that integrates multimodal entity representations while preserving diverse modality-specific characteristics. By effectively adapting and fusing information from diverse modalities, FusionAdapter improves generalization to novel relations with minimal supervision. Extensive experiments on two benchmark MMKG datasets demonstrate that FusionAdapter achieves superior performance over state-of-the-art methods.