3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in multi-modal-entity-alignment
Use these libraries to find multi-modal-entity-alignment models and implementations
No subtasks available.
This work shows that images are particularly useful to align long-tail KG entities, which inherently lack the structural contexts necessary for capturing the correspondences, and provides EVA, a completely unsupervised solution to this problem.
This paper proposes a novel solution called Multi-Modal Entity Alignment (MMEA) to address the problem of entity alignment in a multi-modal view and designs a novel multi- modal knowledge embedding method to generate the entity representations of relational, visual and numerical knowledge.
UMAEA is introduced, a robust multi-modal entity alignment approach designed to tackle uncertainly missing and ambiguous visual modalities, which consistently achieves SOTA performance across all 97 benchmark splits, significantly surpassing existing baselines with limited parameters and time consumption, while effectively alleviating the identified limitations of other models.
Different from previous works, MCLEA considers task-oriented modality and models the inter-modal relationships for each entity representation, and outperforms state-of-the-art baselines on public datasets under both supervised and unsupervised settings.
A novel MMEA transformer is proposed, called MoAlign, that hierarchically introduces neighbor features, multi-modal attributes, and entity types to enhance the alignment task and outperforms strong competitors and achieves excellent entity alignment performance.
DESAlign is proposed, a robust method addressing the over-smoothing caused by semantic inconsistency and interpolating missing semantics using existing modalities using existing modalities, and a training strategy for multi-modal knowledge graph learning based on the proposed generalizable theoretical principle.
This work proposes a novel SnAg method that utilizes a Transformer-based architecture equipped with modality-level noise masking for the robust integration of multi-modal entity features in KGs, and achieves SOTA performance across a total of ten datasets.
PathFusion is proposed, consisting of two main components: MSP, a unified modeling approach that simplifies the alignment process by constructing paths connecting entities and modality nodes to represent multiple modalities; IRF, an iterative fusion method that effectively combines information from different modalities using the path as an information carrier.
MEAformer is introduced, a mlti-modal entity alignment transformer approach for meta modality hybrid, which dynamically predicts the mutual correlation coefficients among modalities for more fine-grained entity-level modality fusion and alignment.
A novel Multi- modal Siamese Network for Entity Alignment (MSNEA) is proposed to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modAL effect.
Adding a benchmark result helps the community track progress.