MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion
It addresses a real-life issue in MMKGC for improving knowledge graph completion, but it is incremental as it builds on existing models to handle missing data.
The paper tackles the problem of missing modalities in multi-modal knowledge graph completion (MMKGC), which hinders modal interaction and model performance, by proposing MACO, a modality adversarial and contrastive framework that generates missing features and achieves state-of-the-art results on public benchmarks.
Recent years have seen significant advancements in multi-modal knowledge graph completion (MMKGC). MMKGC enhances knowledge graph completion (KGC) by integrating multi-modal entity information, thereby facilitating the discovery of unobserved triples in the large-scale knowledge graphs (KGs). Nevertheless, existing methods emphasize the design of elegant KGC models to facilitate modality interaction, neglecting the real-life problem of missing modalities in KGs. The missing modality information impedes modal interaction, consequently undermining the model's performance. In this paper, we propose a modality adversarial and contrastive framework (MACO) to solve the modality-missing problem in MMKGC. MACO trains a generator and discriminator adversarially to generate missing modality features that can be incorporated into the MMKGC model. Meanwhile, we design a cross-modal contrastive loss to improve the performance of the generator. Experiments on public benchmarks with further explorations demonstrate that MACO could achieve state-of-the-art results and serve as a versatile framework to bolster various MMKGC models. Our code and benchmark data are available at https://github.com/zjukg/MACO.