FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
This addresses the challenge of low-resource relation learning in multimodal knowledge graphs, which is important for applications like AI-driven knowledge systems, though it appears incremental as it builds on existing adapter and fusion techniques.
The paper tackles the problem of few-shot relation learning in multimodal knowledge graphs by proposing FusionAdapter, which adapts and fuses modality-specific information to improve generalization to novel relations with minimal supervision, achieving superior performance over state-of-the-art methods on two benchmark datasets.
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.