Pith. sign in

REVIEW 2 major objections 7 minor 300 references

A two-level taxonomy maps graph neural networks onto every stage of the knowledge-graph pipeline.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

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

T0 review · grok-4.5

2026-07-14 19:04 UTC pith:W3TRW4HX

load-bearing objection Solid pipeline-wide GNN–KG survey with a usable two-level taxonomy; organizational value is real, novelty is incremental, and it is ready for referees as a reference piece. the 2 major comments →

arxiv 2607.09666 v1 pith:W3TRW4HX submitted 2026-05-12 cs.LG cs.AIcs.SI

Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey

Chengcheng Sun , Jiayun Tian , Cheng Zhai , Zhixiao Wang , Yajie Song , Xiaobin Rui , Jian Zhang , Philip S. Yu This is my paper
classification cs.LG cs.AIcs.SI
keywords Knowledge GraphsGraph Neural NetworksKnowledge Graph ConstructionKnowledge Graph EmbeddingKnowledge ReasoningGCNGATHGNN
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that Graph Neural Networks have become central to knowledge graphs, yet no prior survey systematically covers GNN methods across the full knowledge-graph technology pipeline. It introduces a two-level taxonomy that crosses four lifecycle stages—construction, embedding, reasoning, and applications—with GNN model families such as GCN, GAT, and hypergraph networks. Under that grid it reviews how each architecture is adapted to tasks like entity extraction, alignment, static and temporal embedding, completion, forecasting, question answering, recommendation, and drug–drug interaction. A reader who works with knowledge graphs cares because the field has been fragmented; a shared map makes strengths, limits, and open gaps easier to compare and act on.

Core claim

Prior reviews treated either knowledge graphs or GNNs in isolation, or only single tasks. This survey establishes that a two-level taxonomy—pipeline stage by GNN architecture—can organize the literature end-to-end, show where message-passing and attention help each stage, and surface unresolved challenges in multimodal, dynamic, low-resource, scalable, and industrial settings.

What carries the argument

The two-level taxonomy framework (knowledge-graph technologies pipeline × GNN-based perspective). It places every reviewed model into construction, embedding, reasoning, or applications and into families such as GCN, GAT, and HGNN so methods can be compared by task fit and architectural bias.

Load-bearing premise

That the four pipeline stages plus the chosen GNN families form a complete, non-overlapping map so every important paper can be cleanly placed.

What would settle it

A large body of high-impact GNN–knowledge-graph work that cannot be assigned to construction, embedding, reasoning, or applications without force, or that depends on architectures outside the survey’s GCN/GAT/HGNN-style families and is essential to the pipeline, would show the taxonomy is incomplete.

Watch this falsifier. Get emailed when new claim-graph text bears on it.

If this is right

  • New GNN–knowledge-graph papers can be located on a shared grid instead of ad-hoc categories.
  • Task designers can match inductive biases (attention, hyperedges, temporal dynamics) to pipeline stages with clearer guidance.
  • Open challenges—multimodal fusion, real-time dynamic updates, few-shot learning, scalability, and industrial deployment—become shared targets.
  • Later surveys and benchmarks can reuse the same axes to check coverage.
  • Strengths and limits of representative models become easier to compare stage by stage.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same grid can later absorb LLM–knowledge-graph hybrids as a cross-cutting layer once retrieval-augmented and graph-prompt methods stabilize.
  • If adopted, industrial platforms may catalog GNN modules by pipeline stage, lowering integration cost.
  • Coverage claims will be stress-tested by continuous-time or foundation-model graph methods that resist clean placement in the four stages or three GNN families.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 7 minor

Summary. This survey argues that prior reviews have not systematically covered GNN methods across the full knowledge-graph technology pipeline, and proposes a two-level taxonomy (KG pipeline stages × GNN architectures / graph-construction styles) to fill that gap. The pipeline is partitioned into construction (extraction, fusion), embedding (static, dynamic, complex), reasoning (completion, prediction), and applications (KGQA, recommendation, NLP, DDI, KG-augmented LLMs). For each stage the authors review representative GNN models, emphasize graph-construction choices and architectures (GCN, GAT, HGNN and variants), summarize strengths and limitations, and close with open issues (multimodal fusion, dynamic updates, low-resource settings, scalability, industrial deployment) and future directions. Tables 1–5 map dozens of models to construction strategy and GNN type; Sections 2–3 fix notation and the taxonomy; Sections 4–7 deliver the stage-wise reviews.

Significance. If the organizational claim holds, the paper supplies a usable map of a large and fragmented literature that practitioners and newcomers can navigate by pipeline stage and GNN family. The consistent dual lens (graph construction + architecture) in Tables 1–5, the explicit strengths/limitations discussion, and the inclusion of recent KG–LLM work are concrete contributions. The work does not claim new algorithms or empirical results; its value is taxonomic and bibliographic. That is appropriate for a survey and is useful provided the coverage and selection criteria are transparent.

major comments (2)
  1. Section 1 and the abstract assert a lack of systematic reviews of GNN methods across the entire KG pipeline and present the two-level taxonomy as filling that gap. Related surveys [35–41] are cited but only briefly distinguished. A short, explicit comparison table (scope, pipeline stages covered, GNN families, year) is needed so that the novelty claim is checkable rather than asserted. Without it, the central organizational claim remains under-supported.
  2. Section 3 and Figure 4 introduce the four-stage pipeline and the GCN/GAT/HGNN families as the organizing frame, yet the manuscript never states inclusion/exclusion criteria, search strategy, or time window for the models in Tables 1–5. Soft or unstated selection criteria make it hard to assess completeness and bias (e.g., under-representation of spectral methods, Graph Transformers, or non-message-passing GNNs). A brief methods paragraph on how papers were chosen would make the taxonomy’s coverage claim falsifiable and strengthen the survey.
minor comments (7)
  1. Figure 1 (timeline of KG review development) is rendered with heavily garbled text in the manuscript PDF; labels are unreadable. Redraw or re-export so the timeline is legible.
  2. Figure 4 (taxonomy) and several other figures (e.g., Fig. 2 pipeline, Fig. 5 extraction diagrams) show similar encoding/OCR artifacts. Ensure all figures are clean vector or high-resolution exports.
  3. Abstract and §1: “detailed review” / “we detailed review” — fix grammar (“we provide a detailed review”).
  4. §2.1: triple notation G=(E1,R,E2) is nonstandard relative to the usual G=(E,R,T) or (h,r,t); a one-sentence alignment with conventional notation would help readers.
  5. Tables 1–5 are dense and useful; adding a short caption note on how “GNN” and “Graph Construction” columns were assigned (author-reported vs. reclassified) would improve reproducibility of the taxonomy.
  6. §8 open issues correctly flag multimodal fusion, dynamic KGs, low-resource settings, scalability, and industrial deployment; a sentence linking each open issue back to specific gaps in Tables 1–5 would tighten the connection between the review and the future-work agenda.
  7. Occasional self-citations of the authors’ prior GNN work appear in the preliminaries; they are not load-bearing but should be balanced with standard GCN/GAT references already present.

Circularity Check

0 steps flagged

No significant circularity: organizational survey taxonomy does not reduce any claim to its inputs by construction or self-citation chain.

full rationale

This is a literature survey whose central claim is organizational (a two-level taxonomy of KG pipeline stages × GNN families, plus a claim that prior reviews lack full-pipeline GNN coverage). There are no fitted parameters, no quantitative predictions, no uniqueness theorems, and no equations that equal their inputs by construction. The gap claim is supported by external surveys (e.g., [38–41] and earlier KG reviews), not by the authors’ own prior results. Occasional self-citations (e.g., the authors’ LGAT / heterogeneous-GNN papers) appear only as surveyed model instances inside Tables 1–5 and are not load-bearing for the taxonomy or the gap claim. Soft inclusion criteria and the completeness of the four-stage partition are ordinary survey limitations, not circular reductions. The derivation chain is therefore self-contained against external literature; score 0 with empty steps is the correct outcome.

Axiom & Free-Parameter Ledger

0 free parameters · 3 axioms · 1 invented entities

As a survey the paper rests on standard definitions of knowledge graphs and GNNs, on a conventional four-stage KG pipeline, and on the authors’ choice of which GNN families and graph-construction styles to treat as primary. No numerical free parameters are fitted. The main invented construct is the two-level taxonomy itself.

axioms (3)
  • domain assumption A knowledge graph is adequately formalized as a set of triples (or hyper-relational / multimodal extensions) whose nodes and edges can be processed by message-passing GNNs.
    Stated in Section 2.1 and used throughout as the object of study.
  • domain assumption The KG technology lifecycle is exhaustively partitioned into construction, embedding, reasoning, and applications.
    Introduced in Section 3 / Figure 4; every subsequent section is organized under this partition.
  • ad hoc to paper GCN, GAT, and HGNN (plus close variants) are the primary architectural families needed to categorize GNN–KG work.
    Chosen as the second level of the taxonomy; other GNN styles are treated as secondary or folded into these bins.
invented entities (1)
  • Two-level taxonomy (KG pipeline × GNN architecture / graph-construction style) no independent evidence
    purpose: To claim systematic coverage of GNN methods across the full knowledge-graph lifecycle and to structure the literature review.
    Presented as the paper’s main organizational contribution (Abstract, Section 3, Figure 4). It is a classification scheme, not an independently measurable physical or computational object.

pith-pipeline@v1.1.0-grok45 · 52718 in / 2454 out tokens · 29180 ms · 2026-07-14T19:04:16.884531+00:00 · methodology

0 comments
read the original abstract

Graph Neural Networks (GNNs) have emerged as a powerful paradigm in Knowledge Graphs (KGs) due to their intrinsic ability to model graph-structured data. However, there remains a lack of a systematic review about GNN-based methodologies across the entire knowledge graph technologies pipeline. To address this gap, we first propose a novel two-level taxonomy framework for GNN-based knowledge graph technologies: the KG technologies pipeline and GNN-based perspective. Specifically, the knowledge graph technologies pipeline covers knowledge graph construction, knowledge graph embedding, knowledge reasoning and knowledge graph applications. Meanwhile, the GNN-based perspective provides a new categorization of knowledge graph technologies with GNN models, such as GCN, GAT, and HGNN. Then, we analyze the advantages of GNN technology based on the characteristics of different tasks in the knowledge graph lifecycle. Furthermore, we detailed review various GNN-based models for knowledge graph following the proposed taxonomy, and summarize strengths and limitations. Finally, we discuss unresolved challenges and outline promising directions for future research.

Figures

Figures reproduced from arXiv: 2607.09666 by Chengcheng Sun, Cheng Zhai, Jian Zhang, Jiayun Tian, Philip S. Yu, Xiaobin Rui, Yajie Song, Zhixiao Wang.

Figure 1
Figure 1. Figure 1: Timeline of the knowledge graph review development. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Knowledge graph technologies pipeline. At present, a large number of knowledge graphs have emerged, of which the representative ones are OpenKN [44], CN-Dbpedia [45], DBpedia [46], Freebase [47], NELL [48], YAGO [49] and so on. In addition to the widespread development of open-domain knowledge graphs, many domain-specific knowledge graphs [50–54] have also been proposed and gradually constructed in recent … view at source ↗
Figure 3
Figure 3. Figure 3: GCN and GAT. Unlike the GCN uniform weighting operation, GAT [59] captures local information in the graph structure by introducing a self-attention mechanism in Figure 3b. This allows GAT to assign different weights to the connections between a node and its neighbors based on the relationships and feature similarities between the nodes [60]. The core idea of GAT is to compute attention coefficients for eac… view at source ↗
Figure 4
Figure 4. Figure 4: Taxonomy of GNN-based knowledge graph techniques. [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Different knowledge extraction tasks: Named Entity Recognition, Relation Extraction, and Joint Extraction. [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Entity alignment and linking: (a) Entity alignment, identifying and matching equivalent entities in two knowledge graphs. (b) [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: A list of shapes of KGs (including Static KG, temporal KG, hyper-relation KG, and multimodal KG). [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Inference for completion and prediction: (a) Example of knowledge graph completion. The dashed arrows are the relationships [PITH_FULL_IMAGE:figures/full_fig_p016_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Applications of knowledge graphs in AI systems [PITH_FULL_IMAGE:figures/full_fig_p018_9.png] view at source ↗

discussion (0)

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

Reference graph

Works this paper leans on

300 extracted references · 10 linked inside Pith

  1. [1]

    Knowledge graphs: Opportunities and challenges.Artificial Intelligence Review, 56(11):13071–13102, 2023

    Ciyuan Peng, Feng Xia, Mehdi Naseriparsa, and Francesco Osborne. Knowledge graphs: Opportunities and challenges.Artificial Intelligence Review, 56(11):13071–13102, 2023

    2023

  2. [2]

    Bolt defect classification algorithm based on knowledge graph and feature fusion.Energy Reports, 8:856–863, 2022

    Yinghui Kong, Xu Liu, Zhenbing Zhao, Dongxia Zhang, and Jikun Duan. Bolt defect classification algorithm based on knowledge graph and feature fusion.Energy Reports, 8:856–863, 2022

    2022

  3. [3]

    A survey of techniques for constructing chinese knowledge graphs and their applications

    Tianxing Wu, Guilin Qi, Cheng Li, and Meng Wang. A survey of techniques for constructing chinese knowledge graphs and their applications. Sustainability, 10(9):3245, 2018

    2018

  4. [4]

    A survey on cybersecurity knowledge graph construction.Computers & Security, 136:103524, 2024

    Xiaojuan Zhao, Rong Jiang, Yue Han, Aiping Li, and Zhichao Peng. A survey on cybersecurity knowledge graph construction.Computers & Security, 136:103524, 2024

    2024

  5. [5]

    Domain-specific knowledge graphs: A survey.Journal of Network and Computer Applications, 185:103076, 2021

    Bilal Abu-Salih. Domain-specific knowledge graphs: A survey.Journal of Network and Computer Applications, 185:103076, 2021

    2021

  6. [6]

    A decade of scholarly research on open knowledge graphs

    Houcemeddine Turki, Abraham Toluwase Owodunni, Mohamed Ali Hadj Taieb, René Fabrice Bile, and Mohamed Ben Aouicha. A decade of scholarly research on open knowledge graphs. InLREC/COLING, pages 438–448. ELRA and ICCL, 2024

    2024

  7. [7]

    Generative knowledge graph construction: A review

    Hongbin Ye, Ningyu Zhang, Hui Chen, and Huajun Chen. Generative knowledge graph construction: A review. In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors,Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1–17, Abu Dhabi, United Arab Emirates, December 2022. Association for Computational Linguistics

    2022

  8. [8]

    Multi-modal knowledge graph construction and application: A survey.IEEE Transactions on Knowledge and Data Engineering, 36(2):715–735, 2022

    Xiangru Zhu, Zhixu Li, Xiaodan Wang, Xueyao Jiang, Penglei Sun, Xuwu Wang, Yanghua Xiao, and Nicholas Jing Yuan. Multi-modal knowledge graph construction and application: A survey.IEEE Transactions on Knowledge and Data Engineering, 36(2):715–735, 2022

    2022

  9. [9]

    Knowledge graphs.ACM Computing Surveys (Csur), 54(4):1–37, 2021

    Aidan Hogan, Eva Blomqvist, Michael Cochez, Claudia d’Amato, Gerard De Melo, Claudio Gutierrez, Sabrina Kirrane, José Emilio Labra Gayo, Roberto Navigli, Sebastian Neumaier, et al. Knowledge graphs.ACM Computing Surveys (Csur), 54(4):1–37, 2021

    2021

  10. [10]

    A survey on knowledge graphs: Representation, acquisition, and applications.IEEE transactions on neural networks and learning systems, 33(2):494–514, 2021

    Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, and S Yu Philip. A survey on knowledge graphs: Representation, acquisition, and applications.IEEE transactions on neural networks and learning systems, 33(2):494–514, 2021

    2021

  11. [11]

    A comprehensive survey on automatic knowledge graph construction.ACM Computing Surveys, 56(4):1–62, 2023

    Lingfeng Zhong, Jia Wu, Qian Li, Hao Peng, and Xindong Wu. A comprehensive survey on automatic knowledge graph construction.ACM Computing Surveys, 56(4):1–62, 2023

    2023

  12. [12]

    A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal.IEEE Trans

    Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, Fuchun Sun, and Kunlun He. A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal.IEEE Trans. Pattern Anal. Mach. Intell., 46(12):9456–9478, 2024

    2024

  13. [13]

    A comprehensive overview of knowledge graph completion.Knowledge-Based Systems, 255:109597, 2022

    Tong Shen, Fu Zhang, and Jingwei Cheng. A comprehensive overview of knowledge graph completion.Knowledge-Based Systems, 255:109597, 2022

    2022

  14. [14]

    Knowledge graph embedding: A survey from the perspective of representation spaces.ACM Computing Surveys, 56(6):1–42, 2024

    Jiahang Cao, Jinyuan Fang, Zaiqiao Meng, and Shangsong Liang. Knowledge graph embedding: A survey from the perspective of representation spaces.ACM Computing Surveys, 56(6):1–42, 2024

    2024

  15. [15]

    Nasrullah Khan, Zongmin Ma, Aman Ullah, and Kemal Polat. Categorization of knowledge graph based recommendation methods and benchmark datasets from the perspectives of application scenarios: A comprehensive survey.Expert Systems with Applications, 206:117737, 2022

    2022

  16. [16]

    Multilingual question answering systems for knowledge graphs - a survey

    Aleksandr Perevalov, Andreas Both, and Axel-Cyrille Ngonga Ngomo. Multilingual question answering systems for knowledge graphs - a survey. Semantic Web, 15(5):2089–2124, 2024

    2089

  17. [17]

    A survey on knowledge graph-based recommender systems.IEEE Transactions on Knowledge and Data Engineering, 34(8):3549–3568, 2020

    Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, and Qing He. A survey on knowledge graph-based recommender systems.IEEE Transactions on Knowledge and Data Engineering, 34(8):3549–3568, 2020

    2020

  18. [18]

    A survey on knowledge graph-based recommender systems : Extended abstract

    Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, and Qing He. A survey on knowledge graph-based recommender systems : Extended abstract. InICDE, pages 3803–3804. IEEE, 2023

    2023

  19. [19]

    Fusing external knowledge resources for natural language understanding techniques: A survey.Information Fusion, 92:190–204, 2023

    Yuqi Wang, Wei Wang, Qi Chen, Kaizhu Huang, Anh Nguyen, Suparna De, and Amir Hussain. Fusing external knowledge resources for natural language understanding techniques: A survey.Information Fusion, 92:190–204, 2023

    2023

  20. [20]

    A survey of knowledge enhanced pre-trained language models.IEEE Trans

    Linmei Hu, Zeyi Liu, Ziwang Zhao, Lei Hou, Liqiang Nie, and Juanzi Li. A survey of knowledge enhanced pre-trained language models.IEEE Trans. Knowl. Data Eng., 36(4):1413–1430, 2024

    2024

  21. [21]

    A decade of knowledge graphs in natural language processing: A survey

    Phillip Schneider, Tim Schopf, Juraj Vladika, Michael Galkin, Elena Simperl, and Florian Matthes. A decade of knowledge graphs in natural language processing: A survey. InAACL/IJCNLP (1), pages 601–614. Association for Computational Linguistics, 2022

    2022

  22. [22]

    Healthcare knowledge graph construction: A systematic review of the state-of-the-art, open issues, and opportunities.Journal of Big Data, 10(1):81, 2023

    Bilal Abu-Salih, Muhammad Al-Qurishi, Mohammed Alweshah, Mohammad Al-Smadi, Reem Alfayez, and Heba Saadeh. Healthcare knowledge graph construction: A systematic review of the state-of-the-art, open issues, and opportunities.Journal of Big Data, 10(1):81, 2023

    2023

  23. [23]

    Knowledge-augmented graph machine learning for drug discovery: From precision to interpretability

    Zhiqiang Zhong and Davide Mottin. Knowledge-augmented graph machine learning for drug discovery: From precision to interpretability. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5841–5842, 2023

    2023

  24. [24]

    Knowledge graphs in education and employability: A survey on applications and techniques.IEEE Access, 10:80174–80183, 2022

    Yousra Fettach, Mounir Ghogho, and Boualem Benatallah. Knowledge graphs in education and employability: A survey on applications and techniques.IEEE Access, 10:80174–80183, 2022

    2022

  25. [25]

    Semantic knowledge graphs for the news: A review.ACM Computing Surveys, 55(7):1–38, 2022

    Andreas L Opdahl, Tareq Al-Moslmi, Duc-Tien Dang-Nguyen, Marc Gallofré Ocaña, Bjørnar Tessem, and Csaba Veres. Semantic knowledge graphs for the news: A review.ACM Computing Surveys, 55(7):1–38, 2022

    2022

  26. [26]

    News graph: An enhanced knowledge graph for news recommendation

    Danyang Liu, Ting Bai, Jianxun Lian, Xin Zhao, Guangzhong Sun, Ji-Rong Wen, and Xing Xie. News graph: An enhanced knowledge graph for news recommendation. InKaRS@CIKM, volume 2601 ofCEUR Workshop Proceedings, pages 1–7. CEUR-WS.org, 2019

    2019

  27. [27]

    Temporal knowledge graph completion: A survey

    Borui Cai, Yong Xiang, Longxiang Gao, He Zhang, Yunfeng Li, and Jianxin Li. Temporal knowledge graph completion: A survey. InIJCAI, pages 6545–6553. ijcai.org, 2023

    2023

  28. [28]

    Knowledge graph quality management: A comprehensive survey.IEEE Trans

    Bingcong Xue and Lei Zou. Knowledge graph quality management: A comprehensive survey.IEEE Trans. Knowl. Data Eng., 35(5):4969–4988, 2023. Manuscript submitted to ACM Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey 25

    2023

  29. [29]

    Financial time series forecasting with multi-modality graph neural network.Pattern Recognition, 121:108218, 2022

    Dawei Cheng, Fangzhou Yang, Sheng Xiang, and Jin Liu. Financial time series forecasting with multi-modality graph neural network.Pattern Recognition, 121:108218, 2022

    2022

  30. [30]

    A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions.Journal of Big Data, 11(1):18, 2024

    Bharti Khemani, Shruti Patil, Ketan Kotecha, and Sudeep Tanwar. A review of graph neural networks: concepts, architectures, techniques, challenges, datasets, applications, and future directions.Journal of Big Data, 11(1):18, 2024

    2024

  31. [31]

    A comprehensive survey on knowledge graph entity alignment via representation learning.arXiv preprint arXiv:2103.15059, pages 1–27, 2021

    Rui Zhang, Bayu Distiawan Trisedy, Miao Li, Yong Jiang, and Jianzhong Qi. A comprehensive survey on knowledge graph entity alignment via representation learning.arXiv preprint arXiv:2103.15059, pages 1–27, 2021

    Pith/arXiv arXiv 2021

  32. [32]

    A survey of graph neural network methods for relation extraction

    Di Liu, Yungui Zhang, and Zhuoqing Li. A survey of graph neural network methods for relation extraction. In2022 IEEE 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), volume 10, pages 2209–2223. IEEE, 2022

    2022

  33. [33]

    A review: Knowledge reasoning over knowledge graph.Expert systems with applications, 141:112948, 2020

    Xiaojun Chen, Shengbin Jia, and Yang Xiang. A review: Knowledge reasoning over knowledge graph.Expert systems with applications, 141:112948, 2020

    2020

  34. [34]

    Deep learning on knowledge graph for recommender system: A survey.arXiv preprint arXiv:2004.00387, pages 1–21, 2020

    Yang Gao, Yi-Fan Li, Yu Lin, Hang Gao, and Latifur Khan. Deep learning on knowledge graph for recommender system: A survey.arXiv preprint arXiv:2004.00387, pages 1–21, 2020

    Pith/arXiv arXiv 2004

  35. [35]

    A survey on graph neural networks for knowledge graph completion.arXiv preprint arXiv:2007.12374, pages 1–10, 2020

    Siddhant Arora. A survey on graph neural networks for knowledge graph completion.arXiv preprint arXiv:2007.12374, pages 1–10, 2020

    Pith/arXiv arXiv 2007

  36. [36]

    Graph neural networks to improve knowledge graph embedding: A survey

    Ismail Chetoui, Essaid El Bachari, Mohammed El Adnani, and Abdelwahed El Hassan. Graph neural networks to improve knowledge graph embedding: A survey. InInternational Conference on Advanced Intelligent Systems for Sustainable Development, pages 15–25. Springer, 2022

    2022

  37. [37]

    A review of graph neural networks and pretrained language models for knowledge graph reasoning.Neurocomputing, page 128490, 2024

    Jiangtao Ma, Bo Liu, Kunlin Li, Chenliang Li, Fan Zhang, Xiangyang Luo, and Yaqiong Qiao. A review of graph neural networks and pretrained language models for knowledge graph reasoning.Neurocomputing, page 128490, 2024

    2024

  38. [38]

    Entity alignment via graph neural networks: a component-level study

    Yanfeng Shu, Ji Zhang, Guangyan Huang, Chi-Hung Chi, and Jing He. Entity alignment via graph neural networks: a component-level study. World Wide Web, 26(6):4069–4092, 2023

    2023

  39. [39]

    Graph intelligence with large language models and prompt learning

    Jia Li, Xiangguo Sun, Yuhan Li, Zhixun Li, Hong Cheng, and Jeffrey Xu Yu. Graph intelligence with large language models and prompt learning. In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 6545–6554, 2024

    2024

  40. [40]

    A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):9456–9478, 2024

    Ke Liang, Lingyuan Meng, Meng Liu, Yue Liu, Wenxuan Tu, Siwei Wang, Sihang Zhou, Xinwang Liu, Fuchun Sun, and Kunlun He. A survey of knowledge graph reasoning on graph types: Static, dynamic, and multi-modal.IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12):9456–9478, 2024

    2024

  41. [41]

    What is event knowledge graph: A survey.IEEE Transactions on Knowledge and Data Engineering, 35(7):7569–7589, 2022

    Saiping Guan, Xueqi Cheng, Long Bai, Fujun Zhang, Zixuan Li, Yutao Zeng, Xiaolong Jin, and Jiafeng Guo. What is event knowledge graph: A survey.IEEE Transactions on Knowledge and Data Engineering, 35(7):7569–7589, 2022

    2022

  42. [42]

    Introducing the knowledge graph: things, not strings.Official google blog, 5(16):3, 2012

    Amit Singhal et al. Introducing the knowledge graph: things, not strings.Official google blog, 5(16):3, 2012

    2012

  43. [43]

    Learning structured embeddings of knowledge bases

    Antoine Bordes, Jason Weston, Ronan Collobert, and Yoshua Bengio. Learning structured embeddings of knowledge bases. InProceedings of the AAAI conference on artificial intelligence, number 1 in 25, pages 301–306, 2011

    2011

  44. [44]

    Openkn: An open knowledge computational engine for network big data

    Yantao Jia, Yuanzhuo Wang, Xueqi Cheng, Xiaolong Jin, and Jiafeng Guo. Openkn: An open knowledge computational engine for network big data. In2014 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2014), pages 657–664. IEEE, 2014

    2014

  45. [45]

    Cn-dbpedia: A never-ending chinese knowledge extraction system

    Bo Xu, Yong Xu, Jiaqing Liang, Chenhao Xie, Bin Liang, Wanyun Cui, and Yanghua Xiao. Cn-dbpedia: A never-ending chinese knowledge extraction system. InInternational Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, pages 428–438. Springer, 2017

    2017

  46. [46]

    Dbpedia: A nucleus for a web of open data

    Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary Ives. Dbpedia: A nucleus for a web of open data. In international semantic web conference, pages 722–735. Springer, 2007

    2007

  47. [47]

    Freebase: a collaboratively created graph database for structuring human knowledge

    Kurt Bollacker, Colin Evans, Praveen Paritosh, Tim Sturge, and Jamie Taylor. Freebase: a collaboratively created graph database for structuring human knowledge. InProceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250, 2008

    2008

  48. [48]

    Toward an architecture for never-ending language learning

    Andrew Carlson, Justin Betteridge, Bryan Kisiel, Burr Settles, Estevam Hruschka, and Tom Mitchell. Toward an architecture for never-ending language learning. InProceedings of the AAAI conference on artificial intelligence, number 1 in 24, pages 1306–1313, 2010

    2010

  49. [49]

    Yago3: A knowledge base from multilingual wikipedias

    Farzaneh Mahdisoltani, Joanna Biega, and Fabian M Suchanek. Yago3: A knowledge base from multilingual wikipedias. InCIDR, pages 1–12, 2013

    2013

  50. [50]

    The harmonic memory: a knowledge graph of harmonic patterns as a trustworthy framework for computational creativity

    Jacopo de Berardinis, Albert Meroño-Peñuela, Andrea Poltronieri, and Valentina Presutti. The harmonic memory: a knowledge graph of harmonic patterns as a trustworthy framework for computational creativity. InProceedings of the ACM Web Conference 2023, pages 3873–3882, 2023

    2023

  51. [51]

    The world literature knowledge graph

    Marco Antonio Stranisci, Eleonora Bernasconi, Viviana Patti, Stefano Ferilli, Miguel Ceriani, and Rossana Damiano. The world literature knowledge graph. InInternational Semantic Web Conference, pages 435–452. Springer, 2023

    2023

  52. [52]

    The holocaust archival material knowledge graph

    Herminio García-González and Mike Bryant. The holocaust archival material knowledge graph. InInternational Semantic Web Conference, pages 362–379. Springer, 2023

    2023

  53. [53]

    Kg-treat: Pre-training for treatment effect estimation by synergizing patient data with knowledge graphs

    Ruoqi Liu, Lingfei Wu, and Ping Zhang. Kg-treat: Pre-training for treatment effect estimation by synergizing patient data with knowledge graphs. InProceedings of the AAAI Conference on Artificial Intelligence, number 8 in 38, pages 8805–8814, 2024

    2024

  54. [54]

    Seqcare: Sequential training with external medical knowledge graph for diagnosis prediction in healthcare data

    Yongxin Xu, Xu Chu, Kai Yang, Zhiyuan Wang, Peinie Zou, Hongxin Ding, Junfeng Zhao, Yasha Wang, and Bing Xie. Seqcare: Sequential training with external medical knowledge graph for diagnosis prediction in healthcare data. InProceedings of the ACM Web Conference 2023, pages 2819–2830, 2023

    2023

  55. [55]

    A new model for learning in graph domains

    Marco Gori, Gabriele Monfardini, and Franco Scarselli. A new model for learning in graph domains. InProceedings. 2005 IEEE international joint conference on neural networks, 2005., volume 2, pages 729–734. IEEE, 2005

    2005

  56. [56]

    Deep learning on graphs: A survey.IEEE Transactions on Knowledge and Data Engineering, 34(1):249–270, 2020

    Ziwei Zhang, Peng Cui, and Wenwu Zhu. Deep learning on graphs: A survey.IEEE Transactions on Knowledge and Data Engineering, 34(1):249–270, 2020. Manuscript submitted to ACM 26 C. Sun et al

    2020

  57. [57]

    A comprehensive survey on graph neural networks

    Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020

    2020

  58. [58]

    Uzair Aslam Bhatti, Hao Tang, Guilu Wu, Shah Marjan, and Aamir Hussain. Deep learning with graph convolutional networks: An overview and latest applications in computational intelligence.International Journal of Intelligent Systems, 2023(1):8342104, 2023

    2023

  59. [59]

    Graph attention networks.stat, 1050(20):10–48550, 2017

    Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio, et al. Graph attention networks.stat, 1050(20):10–48550, 2017

    2017

  60. [60]

    Attention-based graph neural networks: a survey.Artif

    Chengcheng Sun, Chenhao Li, Xiang Lin, Tianji Zheng, Fanrong Meng, Xiaobin Rui, and Zhixiao Wang. Attention-based graph neural networks: a survey.Artif. Intell. Rev., 56(Suppl 2):2263–2310, August 2023

    2023

  61. [61]

    Lgat: a light graph attention network focusing on message passing for semi-supervised node classification.Computing, 106(6):1729–1747, 2024

    Chengcheng Sun, Fanrong Meng, Chenhao Li, Xiaobin Rui, and Zhixiao Wang. Lgat: a light graph attention network focusing on message passing for semi-supervised node classification.Computing, 106(6):1729–1747, 2024

    2024

  62. [62]

    A supervised multi-head self-attention network for nested named entity recognition

    Yongxiu Xu, Heyan Huang, Chong Feng, and Yue Hu. A supervised multi-head self-attention network for nested named entity recognition. In Proceedings of the AAAI conference on artificial intelligence, number 16 in 35, pages 14185–14193, 2021

    2021

  63. [63]

    Mapre: An effective semantic mapping approach for low-resource relation extraction

    Manqing Dong, Chunguang Pan, and Zhipeng Luo. Mapre: An effective semantic mapping approach for low-resource relation extraction. In EMNLP (1), pages 2694–2704. Association for Computational Linguistics, 2021

    2021

  64. [64]

    Joint extraction of entities and relations based on a novel decomposition strategy

    Bowen Yu, Zhenyu Zhang, Xiaobo Shu, Tingwen Liu, Yubin Wang, Bin Wang, and Sujian Li. Joint extraction of entities and relations based on a novel decomposition strategy. InECAI 2020, pages 2282–2289. IOS Press, 2020

    2020

  65. [65]

    Toward practical entity alignment method design: Insights from new highly heterogeneous knowledge graph datasets

    Xuhui Jiang, Chengjin Xu, Yinghan Shen, Yuanzhuo Wang, Fenglong Su, Zhichao Shi, Fei Sun, Zixuan Li, Jian Guo, and Huawei Shen. Toward practical entity alignment method design: Insights from new highly heterogeneous knowledge graph datasets. InProceedings of the ACM on Web Conference 2024, pages 2325–2336, 2024

    2024

  66. [66]

    Tempel: Linking dynamically evolving and newly emerging entities.Advances in Neural Information Processing Systems, 35:1850–1866, 2022

    Klim Zaporojets, Lucie-Aimée Kaffee, Johannes Deleu, Thomas Demeester, Chris Develder, and Isabelle Augenstein. Tempel: Linking dynamically evolving and newly emerging entities.Advances in Neural Information Processing Systems, 35:1850–1866, 2022

    2022

  67. [67]

    Multiview feature augmented neural network for knowledge graph embedding.Knowledge- Based Systems, 255:109721, 2022

    Dan Jiang, Ronggui Wang, Lixia Xue, and Juan Yang. Multiview feature augmented neural network for knowledge graph embedding.Knowledge- Based Systems, 255:109721, 2022

    2022

  68. [68]

    Neural latent space model for dynamic networks and temporal knowledge graphs

    Tony Gracious, Shubham Gupta, Arun Kanthali, Rui M Castro, and Ambedkar Dukkipati. Neural latent space model for dynamic networks and temporal knowledge graphs. InProceedings of the AAAI Conference on Artificial Intelligence, number 5 in 35, pages 4054–4062, 2021

    2021

  69. [69]

    Hyperbolic hypergraph neural networks for multi-relational knowledge hypergraph representation.CoRR, abs/2412.12158:1–13, 2024

    Mengfan Li, Xuanhua Shi, Chenqi Qiao, Teng Zhang, and Hai Jin. Hyperbolic hypergraph neural networks for multi-relational knowledge hypergraph representation.CoRR, abs/2412.12158:1–13, 2024

    Pith/arXiv arXiv 2024

  70. [70]

    Message passing for hyper-relational knowledge graphs

    Mikhail Galkin, Priyansh Trivedi, Gaurav Maheshwari, Ricardo Usbeck, and Jens Lehmann. Message passing for hyper-relational knowledge graphs. InEMNLP (1), pages 7346–7359. Association for Computational Linguistics, 2020

    2020

  71. [71]

    Aspectmmkg: A multi-modal knowledge graph with aspect-aware entities

    Jingdan Zhang, Jiaan Wang, Xiaodan Wang, Zhixu Li, and Yanghua Xiao. Aspectmmkg: A multi-modal knowledge graph with aspect-aware entities. InProceedings of the 32nd ACM International Conference on Information and Knowledge Management, pages 3361–3370, 2023

    2023

  72. [72]

    Renn: A rule embedding enhanced neural network framework for temporal knowledge graph completion

    Linlin Zong, Zhenrong Xie, Chi Ma, Xinyue Liu, Xianchao Zhang, and Bo Xu. Renn: A rule embedding enhanced neural network framework for temporal knowledge graph completion. InProceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13919–13928, 2024

    2024

  73. [73]

    Confidence is not timeless: Modeling temporal validity for rule-based temporal knowledge graph forecasting

    Rikui Huang, Wei Wei, Xiaoye Qu, Shengzhe Zhang, Dangyang Chen, and Yu Cheng. Confidence is not timeless: Modeling temporal validity for rule-based temporal knowledge graph forecasting. InProceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10783–10794, 2024

    2024

  74. [74]

    Multi-granularity temporal question answering over knowledge graphs

    Ziyang Chen, Jinzhi Liao, and Xiang Zhao. Multi-granularity temporal question answering over knowledge graphs. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11378–11392, 2023

    2023

  75. [75]

    Unleashing the power of knowledge graph for recommendation via invariant learning

    Shuyao Wang, Yongduo Sui, Chao Wang, and Hui Xiong. Unleashing the power of knowledge graph for recommendation via invariant learning. In Proceedings of the ACM on Web Conference 2024, pages 3745–3755, 2024

    2024

  76. [76]

    Hallucination mitigation in natural language generation from large-scale open-domain knowledge graphs

    Xiao Shi, Zhengyuan Zhu, Zeyu Zhang, and Chengkai Li. Hallucination mitigation in natural language generation from large-scale open-domain knowledge graphs. InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12506–12521, 2023

    2023

  77. [77]

    Kgnn: Knowledge graph neural network for drug-drug interaction prediction

    Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma, and Xiangxiang Zeng. Kgnn: Knowledge graph neural network for drug-drug interaction prediction. InIJCAI, volume 380, pages 2739–2745, 2020

    2020

  78. [78]

    Nested named entity recognition with partially-observed treecrfs

    Yao Fu, Chuanqi Tan, Mosha Chen, Songfang Huang, and Fei Huang. Nested named entity recognition with partially-observed treecrfs. InAAAI, pages 12839–12847. AAAI Press, 2021

    2021

  79. [79]

    Xuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li, Li Lin, Lijie Wen, and Philip S. Yu. Gradient imitation reinforcement learning for low resource relation extraction. InEMNLP (1), pages 2737–2746. Association for Computational Linguistics, 2021

    2021

  80. [80]

    A partition filter network for joint entity and relation extraction

    Zhiheng Yan, Chong Zhang, Jinlan Fu, Qi Zhang, and Zhongyu Wei. A partition filter network for joint entity and relation extraction. InEMNLP (1), pages 185–197. Association for Computational Linguistics, 2021

    2021

Showing first 80 references.