English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent years have seen significant advancements in multi-modal knowledgegraph completion (MMKGC). MMKGC enhances knowledge graph completion (KGC) byintegrating multi-modal entity information, thereby facilitating the discoveryof unobserved triples in the large-scale knowledge graphs (KGs). Nevertheless,existing methods emphasize the design of elegant KGC models to facilitatemodality interaction, neglecting the real-life problem of missing modalities inKGs. The missing modality information impedes modal interaction, consequentlyundermining the model's performance. In this paper, we propose a modalityadversarial and contrastive framework (MACO) to solve the modality-missingproblem in MMKGC. MACO trains a generator and discriminator adversarially togenerate missing modality features that can be incorporated into the MMKGCmodel. Meanwhile, we design a cross-modal contrastive loss to improve theperformance of the generator. Experiments on public benchmarks with furtherexplorations demonstrate that MACO could achieve state-of-the-art results andserve as a versatile framework to bolster various MMKGC models. Our code andbenchmark data are available at https://github.com/zjukg/MACO.

MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion