Pith. sign in

REVIEW 4 cited by

Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.07084 v1 pith:XS3XFMHV submitted 2022-09-15 cs.AI cs.CL

Knowledge Graph Completion with Pre-trained Multimodal Transformer and Twins Negative Sampling

Yichi Zhang , Wen Zhang This is my paper
classification cs.AI cs.CL
keywords knowledgemultimodalnegativesamplingvbkgccompletiongraphmethods
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Knowledge graphs (KGs) that modelings the world knowledge as structural triples are inevitably incomplete. Such problems still exist for multimodal knowledge graphs (MMKGs). Thus, knowledge graph completion (KGC) is of great importance to predict the missing triples in the existing KGs. As for the existing KGC methods, embedding-based methods rely on manual design to leverage multimodal information while finetune-based approaches are not superior to embedding-based methods in link prediction. To address these problems, we propose a VisualBERT-enhanced Knowledge Graph Completion model (VBKGC for short). VBKGC could capture deeply fused multimodal information for entities and integrate them into the KGC model. Besides, we achieve the co-design of the KGC model and negative sampling by designing a new negative sampling strategy called twins negative sampling. Twins negative sampling is suitable for multimodal scenarios and could align different embeddings for entities. We conduct extensive experiments to show the outstanding performance of VBKGC on the link prediction task and make further exploration of VBKGC.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MGDT: MLLM-Guided Diffusion Transformer with Relation-Adaptive Mixture-of-Experts for Multimodal Knowledge Graph Completion

    cs.AI 2026-07 conditional novelty 6.0

    M2GDT, an align-then-diffuse framework with relation-adaptive routing, MLLM-anchored alignment, and a graph diffusion transformer, improves multimodal knowledge graph completion on MKG-W, MKG-Y, and DB15K over prior s...

  2. Time Imprint: Learning Time-Aware Representations in Multi-Modal Knowledge Graphs

    cs.CV 2026-07 conditional novelty 6.0

    Treating time as an entity-level modality with median-K timestamp selection, attention pooling, and three-stage temporal injection yields large link-prediction gains on the hardest multi-modal ambiguity cases.

  3. RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion

    cs.AI 2026-04 unverdicted novelty 6.0

    RADD decouples retrieval and reranking in multi-modal KGC via a relation-aware KGE retriever and conditional discrete denoiser, reporting state-of-the-art results on three benchmarks.

  4. RADD: Retrieval-Augmented Discrete Diffusion for Multi-Modal Knowledge Graph Completion

    cs.AI 2026-04 conditional novelty 5.0

    A retrieve-then-rerank framework using a KGE shortlist and a discrete diffusion reranker reports SOTA MMKGC scores, but the diffusion mechanism is underspecified and not isolated from a generic reranker.