DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion

• URL: http://arxiv.org/abs/2504.06543v1
• Date: Wed, 09 Apr 2025 02:50:37 GMT
• Title: DiffusionCom: Structure-Aware Multimodal Diffusion Model for Multimodal Knowledge Graph Completion
• Authors: Wei Huang, Meiyu Liang, Peining Li, Xu Hou, Yawen Li, Junping Du, Zhe Xue, Zeli Guan,
• Abstract summary: We propose a structure-aware multimodal Diffusion model for multimodal knowledge graph Completion (DiffusionCom)<n>DiffusionCom is trained using both generative and discriminative losses for the generator, while the feature extractor is optimized exclusively with discriminative loss.<n>Experiments on the FB15k-237-IMG and WN18-IMG datasets demonstrate that DiffusionCom outperforms state-of-the-art models.
• Score: 15.898786167134997
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most current MKGC approaches are predominantly based on discriminative models that maximize conditional likelihood. These approaches struggle to efficiently capture the complex connections in real-world knowledge graphs, thereby limiting their overall performance. To address this issue, we propose a structure-aware multimodal Diffusion model for multimodal knowledge graph Completion (DiffusionCom). DiffusionCom innovatively approaches the problem from the perspective of generative models, modeling the association between the $(head, relation)$ pair and candidate tail entities as their joint probability distribution $p((head, relation), (tail))$, and framing the MKGC task as a process of gradually generating the joint probability distribution from noise. Furthermore, to fully leverage the structural information in MKGs, we propose Structure-MKGformer, an adaptive and structure-aware multimodal knowledge representation learning method, as the encoder for DiffusionCom. Structure-MKGformer captures rich structural information through a multimodal graph attention network (MGAT) and adaptively fuses it with entity representations, thereby enhancing the structural awareness of these representations. This design effectively addresses the limitations of existing MKGC methods, particularly those based on multimodal pre-trained models, in utilizing structural information. DiffusionCom is trained using both generative and discriminative losses for the generator, while the feature extractor is optimized exclusively with discriminative loss. This dual approach allows DiffusionCom to harness the strengths of both generative and discriminative models. Extensive experiments on the FB15k-237-IMG and WN18-IMG datasets demonstrate that DiffusionCom outperforms state-of-the-art models.

Related papers

• Scaling Laws for Native Multimodal Models [53.490942903659565]
  We revisit the architectural design of native multimodal models and conduct an extensive scaling laws study. Our investigation reveals no inherent advantage to late-fusion architectures over early-fusion ones. We show that incorporating Mixture of Experts (MoEs) allows for models that learn modality-specific weights, significantly enhancing performance.
  arXiv  Detail & Related papers  (2025-04-10T17:57:28Z)
• Transformer-Based Multimodal Knowledge Graph Completion with Link-Aware Contexts [3.531533402602335]
  Multimodal knowledge graph completion (MMKGC) aims to predict missing links in multimodal knowledge graphs (MMKGs)<n>Existing MMKGC approaches primarily extend traditional knowledge graph embedding (KGE) models.<n>We propose a novel approach that integrates Transformer-based KGE models with cross-modal context generated by pre-trained VLMs.
  arXiv  Detail & Related papers  (2025-01-26T22:23:14Z)
• Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation [51.80447197290866]
  Multi-modal knowledge graph completion (MMKGC) aims to discover unobserved knowledge from given knowledge graphs.<n>Existing MMKGC methods usually extract multi-modal features with pre-trained models.<n>We introduce a novel framework MyGO to tokenize, fuse, and augment the fine-grained multi-modal representations of entities.
  arXiv  Detail & Related papers  (2024-04-15T05:40:41Z)
• Noise-powered Multi-modal Knowledge Graph Representation Framework [52.95468915728721]
  The rise of Multi-modal Pre-training highlights the necessity for a unified Multi-Modal Knowledge Graph representation learning framework.<n>We propose a novel SNAG method that utilizes a Transformer-based architecture equipped with modality-level noise masking.<n>Our approach achieves SOTA performance across a total of ten datasets, demonstrating its versatility.
  arXiv  Detail & Related papers  (2024-03-11T15:48:43Z)
• Structure-Guided Adversarial Training of Diffusion Models [27.723913809313125]
  We introduce Structure-guided Adversarial training of Diffusion Models (SADM) We compel the model to learn manifold structures between samples in each training batch. SADM substantially improves existing diffusion transformers and outperforms existing methods in image generation and fine-tuning tasks.
  arXiv  Detail & Related papers  (2024-02-27T15:05:13Z)
• FedDiff: Diffusion Model Driven Federated Learning for Multi-Modal and Multi-Clients [32.59184269562571]
  We propose a multi-modal collaborative diffusion federated learning framework called FedDiff. Our framework establishes a dual-branch diffusion model feature extraction setup, where the two modal data are inputted into separate branches of the encoder. Considering the challenge of private and efficient communication between multiple clients, we embed the diffusion model into the federated learning communication structure.
  arXiv  Detail & Related papers  (2023-11-16T02:29:37Z)
• MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion [18.188971531961663]
  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.
  arXiv  Detail & Related papers  (2023-08-13T06:29:38Z)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models [77.83923746319498]
  We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models. We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
  arXiv  Detail & Related papers  (2023-05-29T04:22:57Z)
• Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis [96.46952672172021]
  Bi-Bimodal Fusion Network (BBFN) is a novel end-to-end network that performs fusion on pairwise modality representations. Model takes two bimodal pairs as input due to known information imbalance among modalities.
  arXiv  Detail & Related papers  (2021-07-28T23:33:42Z)
• Unsupervised multi-modal Styled Content Generation [61.040392094140245]
  UMMGAN is a novel architecture designed to better model multi-modal distributions in an unsupervised fashion. We show that UMMGAN effectively disentangles between modes and style, thereby providing an independent degree of control over the generated content.
  arXiv  Detail & Related papers  (2020-01-10T19:36:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.