The DOI matches its Crossref record; 357 of the 357 references it cites were found in a registry or an index; 2 of the 78 sources its claims cite were checked for support.
A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal
Open accessAbstract
Knowledge graph reasoning (KGR), aiming to deduce new facts from existing facts based on mined logic rules underlying knowledge graphs (KGs), has become a fast-growing research direction. It has been proven to significantly benefit the usage of KGs in many AI applications, such as question answering, recommendation systems, and etc. According to the graph types, existing KGR models can be roughly divided into three categories, i.e., static models, temporal models, and multi-modal models. Early works in this domain mainly focus on static KGR, and recent works try to leverage the temporal and multi-modal information, which are more practical and closer to real-world. However, no survey papers and open-source repositories comprehensively summarize and discuss models in this important direction. To fill the gap, we conduct a first survey for knowledge graph reasoning tracing from static to temporal and then to multi-modal KGs. Concretely, the models are reviewed based on bi-level taxonomy, i.e., top-level (graph types) and base-level (techniques and scenarios). Besides, the performances, as well as datasets, are summarized and presented. Moreover, we point out the challenges and potential opportunities to enlighten the readers.
Overview
CoChat Summary
TL;DR
This survey reviews knowledge graph reasoning (KGR) across static, temporal, and multi-modal KGs using a bi-level taxonomy of graph types and base-level techniques/scenarios. It summarizes 90 static, 58 temporal, and 32 multi-modal KGR models, plus datasets and performance comparisons, and highlights open challenges.
Key findings
- The survey organizes KGR into three graph types, fourteen techniques, and four reasoning scenarios; it reviews 90 static KGR models, 58 temporal KGR models, and 32 multi-modal KGR models.
- Static KGR: embedding-based models generally have better expressive ability but lack explainability; GNN-based models are considered most promising, while path-based models suit transductive reasoning and rule-based models naturally support inductive reasoning. Of the static models reviewed, there are 56 transductive and 34 inductive models.
- Temporal KGR: RNN-based models are considered most promising and are more easily adopted to extrapolation; extrapolation reasoning is still early, occupying only around 30% of temporal KGR models. Reported results include TeMP achieving MRR 69.10 and H@10 91.70 on ICEWS05-15, and RPC achieving MRR 22.41 on GDELT.
- Multi-modal KGR: research is still early, with only 18% of models for multi-modal scenarios; reported results include IMF at H@1 28.7 and H@10 59.3 on FB15k-237-IMG, and MoSE at H@1 94.8 and H@10 97.4 on WN18-IMG. The survey also shares 180 state-of-the-art KGR models and 67 typical datasets on GitHub.
Methods
- Literature survey design: the paper defines static, temporal, and multi-modal KGs, formulates KGR tasks, and introduces transductive/inductive and interpolation/extrapolation scenarios.
- Models are reviewed under a bi-level taxonomy: top-level graph types (static, temporal, multi-modal) and base-level techniques and scenarios.
- The survey summarizes typical datasets and performance tables for static, temporal, and multi-modal KGR, and points out challenges and opportunities; an open-source repository accompanies the collection.
Limitations
- The paper does not explicitly state limitations of the survey itself.
- Evident from the text: as a survey, it conducts no new experiments or unified benchmark evaluation; performance comparisons are compiled from prior reported results, and some table entries are missing.
- The text itself notes that several areas remain early-stage, including extrapolation reasoning, multi-modal KGR, out-of-distribution reasoning, and large-scale reasoning.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 7 Not valid · 60 Not checked · 85 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Most of them only focus on static KGR but omit the recent progress in other KGs, i.e., temporal KGs and multi-modal KGs.”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > 1 INTRODUCTION
What the sources say
- Not matchedcites [9] Teru, Inductive relation prediction by subgraph reasoning
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Check pendingcites [10] source
- Partly supportedcites [11] sourceExperimental — accuracy not yet measured
The Related Work subsection 'Static KG Embeddings' (Sec. 2, p. 1-2 of our copy) states that the many methods modelling static KGs 'without temporally dynamic facts' 'have been summarize in recent surveys (Wang et al. 2017; Ji et al. 2020; Dai et al. 2020)' and that 'these methods do not capture temporally dynamic facts' — this supports only the 'surveys cover static KGE' half, and it is a statement about the methods rather than an assessment of the surveys' scope. Our copy nowhere says those surveys omit recent temporal progress: the 'Temporal KG Embeddings' paragraph (Sec. 2) simply reviews TKGE methods without crediting or faulting any survey. Multi-modal KGs are not addressed at all (searched: 'multi-modal knowledge graph embedding', 'survey', 'review'), so that part of the claim has no support in this source; note also that CyGNet is a primary research paper, not a KGR survey. (LLM, conf=0.62)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
In the paper
“Some recent attempts provide potential solutions for inferring unseen entities, which are known as inductive reasoning models, such as [71], [72], [73], [75].”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > 7.1 Out-of-distribution Reasoning
What the sources say
- Check pendingcites [71] source
- Check pendingcites [72] source
- Could not verifycites [73] sourceExperimental — accuracy not yet measured
Our copy of the Wu et al. (2021) survey contains no passage about inductive reasoning models for inferring unseen entities: searches on 'inductive reasoning / unseen entities / knowledge graph completion / generalizing to unseen graphs' returned only the taxonomy sections (A. Background p. 2; A. Taxonomy p. 4) and the Practical Applications section (pp. 16-17), which mention knowledge/semantic graph generation for knowledge discovery [157], [158] and link prediction for recommender systems [161]-[163], plus the reference list entry [11] Battaglia et al. 'Relational inductive biases' — none of which states the attributed claim. The claim's examples ([71], [72], [73], [75] in the citing paper) are not identified anywhere in our copy, and no contrary point is made, so the material is neither supported nor disputed here. (LLM, conf=0.62)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Still, most of the rule-based models are good at inductive scenarios, which is reasonable.”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > 3.2 Review on Reasoning Scenarios
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Among them, 42.57% of the extrapolation models belong to time-operation models, and 47.62% belongs to RNN-based models.”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > 4.2 Review on Reasoning Scenarios
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Also, most of the recent research lies in this type.”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > 4.2 Review on Reasoning Scenarios
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
36 more claims
Create a free account to see all 153 claims and to verify the 58 references still open.
- It may state two separate claims as one. 45
- Probably not a substantial claim. 86
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > Tensor Decompositional Model.
“LowFER [46] 0.465 0.434 0.479 0.526 0.359 0.359 0.266 0.396”
§ A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multi-Modal > Tensor Decompositional Model.
“Methods WN18RR FB15K-237 MRR H@1 H@3 H@10 MRR H@1 H@3 H@10”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“The triple part is the subset of a classical KG dataset WN18 [215], and the images are extracted from ImageNet [237].”
MethodLanguage Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“3) GNN Model: Graph neural networks (GNN) [72], [73] are widely used for graph tasks, due to their promising capacity for structural information mining.”
BackgroundA simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Graph neural networks: A review of methods and applications
Zhou, J., Cui, G., Hu, S., Zhang, Z., Yang, C., Liu, Z., Wang, L., Li, C., & Sun, M. (2020) · AI Open · doi:10.1016/j.aiopen.2021.01.001 · Cited by 6,880
Recent advances in convolutional neural networks
Gu, J., Wang, Z., Kuen, J., Ma, L., Shahroudy, A., Shuai, B., Liu, T., Wang, X., Wang, G., Cai, J., et al. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2017.10.013 · Cited by 6,576
Research works printed but not linked: 12
- Ren, Query2Box: Reasoning over knowledge graphs in vector space using box embeddings, 1
- 10.5555/3524938.3525087 · doi:10.5555/3524938.3525087
- Huang, A theory of link prediction via relational weisfeiler-leman
- Cheng, Differentiable neuro-symbolic reasoning on large-scale knowledge graphs
- Zhang, Temporal knowledge graph completion with approximated Gaussian process embedding, 4697
- Sadeghian, Temporal reasoning over event knowledge graphs, 1
- 10.18653/v1/d18-1516 · DOI · Paper page
- 10.18653/v1/2020.emnlp-main.462 · DOI · Paper page
- 10.18653/v1/d19-1269 · DOI
- 10.18653/v1/d17-1060 · DOI · Paper page
- Mahdisoltani, 2013, YAGO3: A knowledge base from multilingual Wikipedias
- 10.18653/v1/d18-1516 · DOI · Paper page
Cited by
Reasoning with Language Model Prompting: A Survey
Qiao, S., Ou, Y., Zhang, N., Chen, X., Yao, Y., Deng, S., Tan, C., Huang, F., & Chen, H. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.294 · Cited by 512
Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
Agrawal, G., Kumarage, T., Alghamdi, Z., & Liu, H. (2024) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2024.naacl-long.219 · Cited by 331
LLMs for knowledge graph construction and reasoning: recent capabilities and future opportunities
Zhu, Y., Wang, X., Chen, J., Qiao, S., Ou, Y., Yao, Y., Deng, S., Chen, H., & Zhang, N. (2024) · World Wide Web · doi:10.1007/s11280-024-01297-w · Cited by 294
LLMRec: Large Language Models with Graph Augmentation for Recommendation
Wei, W., Ren, X., Tang, J., Wang, Q., Su, L., Cheng, S., Wang, J., Yin, D., & Huang, C. (2024) · Proceedings of the 17th ACM International Conference on Web Search and Data Mining · doi:10.1145/3616855.3635853 · Cited by 268
Cluster-Guided Contrastive Graph Clustering Network
Yang, X., Liu, Y., Zhou, S., Wang, S., Tu, W., Zheng, Q., Liu, X., Fang, L., & Zhu, E. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i9.26285 · Cited by 242
Self-citation
Metadata
- Authors
- Liang, K., Meng, L., Liu, M., Liu, Y., Tu, W., Wang, S., Zhou, S., Liu, X., Sun, F., & He, K.
- Affiliations
- National University of Defense Technology (CN)
- Tsinghua University (CN)
- Chinese PLA General Hospital (CN)
- ORCID
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2024-12
- Volume
- 46
- Issue
- 12
- Pages
- 9456-9478
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W4400111732
- Cited by
- 553
- References
- 336
- Citations by year
- 2026: 208 · 2025: 188 · 2024: 114
- FWCI
- 42.52
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Natural Science Foundation of China (62325604, 62276271)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Advanced Graph Neural Networks
- Physical Sciences › Computer Science › Artificial Intelligence › Semantic Web and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- knowledge graph reasoning, temporal knowledge graphs, multimodal knowledge graphs, temporal reasoning, multimodal reasoning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-11-18, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-18 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.