Pith. sign in

REVIEW 5 cited by

SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models

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 2203.02167 v1 pith:WV6QO74T submitted 2022-03-04 cs.CL

Liang Wang , Wei Zhao , Zhuoyu Wei , Jingming Liu This is my paper · ORCID
classification cs.CL
keywords methodsnegativesgraphsimkgccompletioncontrastiveembedding-basedinductive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Knowledge graph completion (KGC) aims to reason over known facts and infer the missing links. Text-based methods such as KGBERT (Yao et al., 2019) learn entity representations from natural language descriptions, and have the potential for inductive KGC. However, the performance of text-based methods still largely lag behind graph embedding-based methods like TransE (Bordes et al., 2013) and RotatE (Sun et al., 2019b). In this paper, we identify that the key issue is efficient contrastive learning. To improve the learning efficiency, we introduce three types of negatives: in-batch negatives, pre-batch negatives, and self-negatives which act as a simple form of hard negatives. Combined with InfoNCE loss, our proposed model SimKGC can substantially outperform embedding-based methods on several benchmark datasets. In terms of mean reciprocal rank (MRR), we advance the state-of-the-art by +19% on WN18RR, +6.8% on the Wikidata5M transductive setting, and +22% on the Wikidata5M inductive setting. Thorough analyses are conducted to gain insights into each component. Our code is available at https://github.com/intfloat/SimKGC .

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Systematic Evaluation of Knowledge Graph Repair with Large Language Models

    cs.DB 2025-07 conditional novelty 7.0 of 10

    A systematic VIO-based framework generates SHACL-violating graph test cases and shows that LLM repair systems perform best with concise, violation-focused prompts.

  2. HERGC: Heterogeneous Experts Representation and Generative Completion for Multimodal Knowledge Graphs

    cs.CL 2025-06 conditional novelty 6.0 of 10

    HERGC combines a multimodal expert-based retriever with a fine-tuned LLM re-ranker to achieve state-of-the-art multimodal knowledge graph completion on MKG-W, MKG-Y, and DB15K.

  3. AgREE: Agentic Reasoning for Knowledge Graph Completion on Emerging Entities

    cs.AI 2025-08 conditional novelty 5.0 of 10

    A zero-training LLM agent that iteratively retrieves and reflects over search results can complete knowledge graph triples about emerging entities better than trained KGC models, the authors report.

  4. KG-BiLM: Knowledge Graph Embedding via Bidirectional Language Models

    cs.CL 2025-06 conditional novelty 4.0 of 10

    A bidirectional decoder with a graph-aware attention mask, knowledge-masked prediction, and contrastive sub-graph alignment achieves reported state-of-the-art link prediction on Wikidata5M and competitive results on WN18RR.

  5. Towards Structure-aware Model for Multi-modal Knowledge Graph Completion

    cs.MM 2025-05 conditional novelty 4.0 of 10

    TSAM combines token-level fusion of visual and textual data with structure-anchored contrastive learning, outperforming prior multi-modal KGC models on DB15K, MKG-W, and MKG-Y.

Pith tools