End-to-end multimodal learning on knowledge graphs has been left largely unaddressed. Instead, most end-to-end models such as message passing networks learn solely from the relational information encoded in graphs structure: raw values, or literals, are either omitted completely or are stripped from their values and treated as regular nodes. In either case we lose potentially relevant information which could have otherwise been exploited by our learning methods. To avoid this, we must treat literals and non-literals as separate cases. We must also address each modality separately and accordingly: numbers, texts, images, geometries, et cetera. We propose a multimodal message passing network which not only learns end-to-end from the structure of graphs, but also from their possibly divers set of multimodal node features. Our model uses dedicated (neural) encoders to naturally learn embeddings for node features belonging to five different types of modalities, including images and geometries, which are projected into a joint representation space together with their relational information. We demonstrate our model on a node classification task, and evaluate the effect that each modality has on the overall performance. Our result supports our hypothesis that including information from multiple modalities can help our models obtain a better overall performance.
تحميل البحث