Elamur Research⌕
☰
home / papers / 2026 / GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion

GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion

Paper · 2026 · Qizhuo Xie, Yunhui Liu, Yu Xing et al.

Summary

Knowledge graph completion (KGC) with LLMs faces a mismatch: graph embeddings are dense continuous vectors, while LLMs reason over discrete token sequences. Earlier code-based methods such as SSQR and ReaLM turn embeddings into discrete codes. The authors argue these codes are flat, entangled compressions with no internal semantic order.

GS-Quant builds on RQ-VAE and adds two components:

  • Granular Semantic Enhancement (GSE) aligns successive quantization levels with a hierarchy tree built by clustering. Early codes then encode broad categories and later codes encode finer attributes.
  • Generative Structural Reconstruction (GSR) uses a small GPT-style decoder that takes the code sequence and regenerates both the target entity and its hierarchical ancestors. This gives the codes a causal, sentence-like structure.

Entity inputs combine RotatE-style structural embeddings with PLM encodings of entity names and descriptions. The learned codes are added to the LLM vocabulary, and the model is then fine-tuned to pick the correct entity from a candidate set.

On WN18RR and FB15k-237, the authors report that GS-Quant beats text-based and embedding-based baselines. The work suggests that hierarchically organized discrete codes make graph data easier for LLMs to use.

Key points

  • Benchmarks: FB15k-237 and WN18RR, evaluated with MRR and Hits@1/3/10.
  • Best configurations in the codebook-entropy analysis:
    • FB15k-237: MRR 0.455, Hits@1 0.386, Hits@10 0.592.
    • WN18RR: MRR 0.635, Hits@1 0.594, Hits@10 0.712.
  • Entropy as a selection signal: higher codebook entropy tracked better ranking scores. The authors therefore use entropy to choose model checkpoints.
  • Code structure: visualizations show sparse, globally uniform usage of coarse-level codes and more discriminative fine-level codes. This contrasts with vanilla RQ-VAE.
  • Limitations and availability:
    • Tested only on 7B-scale LLM backbones.
    • Evaluated only on link prediction.
    • Generalization to other knowledge graphs has not been verified.
    • Code is at github.com/mikumifa/GS-Quant.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Nanjing UniversityNanjing · China99 works · 8,510 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 2Research subjects and languages the work is about.Efficient models & compression · 297 worksKnowledge graphs & ontologies · 211 works

Cite

Cite as Qizhuo Xie, Yunhui Liu, Yu Xing, Qianzi Hou, Xudong Jin, Tao Zheng and Tieke He. 2026. GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.765

@inproceedings{xie2026gs,
  title = {{GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion}},
  author = {Qizhuo Xie, Yunhui Liu, Yu Xing, Qianzi Hou, Xudong Jin, Tao Zheng and Tieke He},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.765},
  url = {https://doi.org/10.18653/v1/2026.acl-long.765}
}

References

59 references, 17 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Garima Agrawal, Tharindu Kumarage, Zeyad Alghamdi, and Huan Liu. 2024. Can knowledge graphs reduce hallucinations in llms?: A survey. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Pape… find
  2. Ivana Balazevic, Carl Allen, and Timothy Hospedales. 2019. TuckER: Tensor factorization for knowledge graph completion. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP),…
  3. Antoine Bordes, Nicolas Usunier, Alberto Garcia-Durán, Jason Weston, and Oksana Yakhnenko. 2013. Translating embeddings for modeling multi-relational data. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, NIPS’13, page 2787–2795.
  4. Zongsheng Cao, Qianqian Xu, Zhiyong Yang, Xiaochun Cao, and Qingming Huang. 2022. Geometry interaction knowledge graph embeddings. Proceedings of the AAAI Conference on Artificial Intelligence, 36(5):5521–5529. find
  5. Ines Chami, Adva Wolf, Da-Cheng Juan, Frederic Sala, Sujith Ravi, and Christopher Ré. 2020. Low-dimensional hyperbolic knowledge graph embeddings. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6901–6914, Online. Association for Computational Lingui…
  6. Zhe Chen, Yuehan Wang, Bin Zhao, Jing Cheng, Xin Zhao, and Zongtao Duan. 2020. Knowledge graph completion: A review. Ieee Access, 8:192435– 192456. find
  7. Bonggeun Choi, Daesik Jang, and Youngjoong Ko. 2021. Mem-kgc: Masked entity model for knowledge graph completion with pre-trained language model. IEEE Access, 9:132025–132032. find
  8. DeepSeek-AI, Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, Xiaokang Zhang, Xingkai Yu, Yu Wu, Z. F. Wu, Zhibin Gou, Zhihong Shao, Zhuoshu Li, Ziyi Gao, and 181 others. 2025. Deepseek-r1: Incentivizing reasoning capability in ll…
  9. Lingbing Guo, Zhongpu Bo, Zhuo Chen, Yichi Zhang, Jiaoyan Chen, Lan Yarong, Mengshu Sun, Zhiqiang Zhang, Yangyifei Luo, Qian Li, and 1 others. 2024. Mkgl: mastery of a three-word language. Advances in Neural Information Processing Systems, 37:140509–140534. find
  10. Dawei Li, Zhen Tan, Tianlong Chen, and Huan Liu. 2024. Contextualization distillation from large language model for knowledge graph completion. In Findings of the Association for Computational Linguistics: EACL 2024, pages 458–477. Association for Computational Linguistics.
  11. Qingyu Guo, Fuzhen Zhuang, Chuan Qin, Hengshu Zhu, Xing Xie, Hui Xiong, and Qing He. 2020. A survey on knowledge graph-based recommender systems. IEEE Transactions on Knowledge and Data Engineering, 34(8):3549–3568. find
  12. Muzhi Li, Cehao Yang, Chengjin Xu, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, and Irwin King. 2025. Retrieval, reasoning, re-ranking: A context-enriched framework for knowledge graph completion. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for… find
  13. Wenbin Guo, Xin Wang, Jiaoyan Chen, Lingbing Guo, Zhao Li, and Zirui Chen. 2025. Realm: Residual quantization bridging knowledge graph embeddings and large language models. Preprint, arXiv:2510.09711. — [arXiv:2510.09711](https://arxiv.org/abs/2510.09711) find
  14. Zeyuan Guo, Enmao Diao, Cheng Yang, and Chuan Shi. 2026. Graph tokenization for bridging graphs and transformers. In The Fourteenth International Conference on Learning Representations. find
  15. Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. Hipporag: Neurobiologically inspired long-term memory for large language models. In Advances in Neural Information Processing Systems, volume 37, pages 59532–59569. Curran Associates, Inc.
  16. Yuan He, Moy Yuan, Jiaoyan Chen, and Ian Horrocks. 2024. Language models as hierarchy encoders. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. find
  17. Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations.
  18. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix,… find
  19. Pengcheng Jiang, Lang Cao, Cao Xiao, Parminder Bhatia, Jimeng Sun, and Jiawei Han. 2024. Kg-fit: Knowledge graph fine-tuning upon open-world knowledge. In Advances in Neural Information Processing Systems, volume 37, pages 136220–136258. Curran Associates, Inc. find
  20. Doyup Lee, Chiheon Kim, Saehoon Kim, Minsu Cho, and Wook-Shin Han. 2022. Autoregressive image generation using residual quantization. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11513–11522. find
  21. Qika Lin, Tianzhe Zhao, Kai He, Zhen Peng, Fangzhi Xu, Ling Huang, Jingying Ma, and Mengling Feng. 2025. Self-supervised quantized representation for seamlessly integrating knowledge graphs with large language models. In Proceedings of the 63rd Annual Meeting of the Association for Computational Lin… find
  22. Ben Liu, Jihai Zhang, Fangquan Lin, Cheng Yang, and Min Peng. 2025a. Filter-then-generate: Large language models with structure-text adapter for knowledge graph completion. In Proceedings of the 31st International Conference on Computational Linguistics, pages 11181–11195. find
  23. Yang Liu, Zequn Sun, Guangyao Li, and Wei Hu. 2022. I know what you do not know: Knowledge graph embedding via co-distillation learning. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, CIKM ’22, page 1329–1338, New York, NY, USA. Association for Computi… find
  24. Yang Liu, Xiaobin Tian, Zequn Sun, and Wei Hu. 2024. Finetuning generative large language models with discrimination instructions for knowledge graph completion. In The Semantic Web – ISWC 2024: 23rd International Semantic Web Conference, Baltimore, MD, USA, November 11–15, 2024, Proceedings, Part I… find
  25. Yu Liu, Yanan Cao, Xixun Lin, Yanmin Shang, Shi Wang, and Shirui Pan. 2025b. Enhancing large language model for knowledge graph completion via structure-aware alignment-tuning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20981–20995. find
  26. Chuangtao Ma, Yongrui Chen, Tianxing Wu, Arijit Khan, and Haofen Wang. 2025. Large language models meet knowledge graphs for question answering: Synthesis and opportunities. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 24589–24608, Suzhou, China. A… find
  27. Yueen Ma, Zixing Song, Xuming Hu, Jingjing Li, Yifei Zhang, and Irwin King. 2023. Graph component contrastive learning for concept relatedness estimation. In Proceedings of the AAAI Conference on Artificial Intelligence, pages 13362–13370. find
  28. Daniel Müllner. 2011. Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378. — [arXiv:1109.2378](https://arxiv.org/abs/1109.2378) find
  29. Deepak Nathani, Jatin Chauhan, Charu Sharma, and Manohar Kaul. 2019. Learning attention-based embeddings for relation prediction in knowledge graphs. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4710– 4723, Florence, Italy. Association for Computa…
  30. Long Ouyang, Jeff Wu, Xu Jiang, Diogo Almeida, Carroll L. Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul Christiano, Jan Leike, and Ryan Lowe. 2022. Train…
  31. Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, and Xindong Wu. 2024. Unifying large language models and knowledge graphs: A roadmap. IEEE Transactions on Knowledge and Data Engineering, pages 1–20.
  32. Boci Peng, Yun Zhu, Yongchao Liu, Xiaohe Bo, Haizhou Shi, Chuntao Hong, Yan Zhang, and Siliang Tang. 2024. Graph retrieval-augmented generation: A survey. ACM Transactions on Information Systems.
  33. Michael Schlichtkrull, Thomas N Kipf, Peter Bloem, Rianne Van Den Berg, Ivan Titov, and Max Welling. 2018. Modeling relational data with graph convolutional networks. In European semantic web conference, pages 593–607. Springer. find
  34. Zixing Song, Yueen Ma, and Irwin King. 2022. Individual fairness in dynamic financial networks. In NeurIPS 2022 Workshop: New Frontiers in Graph Learning. find
  35. Zixing Song, Ziqiao Meng, and Irwin King. 2024. A diffusion-based pre-training framework for crystal property prediction. In AAAI, pages 8993–9001. AAAI Press. find
  36. Zixing Song, Yifei Zhang, and Irwin King. 2023a. No change, no gain: Empowering graph neural networks with expected model change maximization for active learning. In NeurIPS. find
  37. Zixing Song, Yifei Zhang, and Irwin King. 2023b. Optimal block-wise asymmetric graph construction for graph-based semi-supervised learning. In NeurIPS. find
  38. Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel Ni, Heung-Yeung Shum, and Jian Guo. 2024. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In The Twelfth International Conference on Learning Representations. find
  39. Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. 2019. Rotate: Knowledge graph embedding by relational rotation in complex space. In International Conference on Learning Representations.
  40. Joshua B Tenenbaum, Charles Kemp, Thomas L Griffiths, and Noah D Goodman. 2011. How to grow a mind: Statistics, structure, and abstraction. science, 331(6022):1279–1285. find
  41. Théo Trouillon, Johannes Welbl, Sebastian Riedel, Eric Gaussier, and Guillaume Bouchard. 2016. Complex embeddings for simple link prediction. In Proceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 2071–2080, New York, New…
  42. Aaron van den Oord, Oriol Vinyals, and koray kavukcuoglu. 2017. Neural discrete representation learning. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc. find
  43. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research, 9(86):2579–2605. find
  44. Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, and Partha Talukdar. 2020. Composition-based multi-relational graph convolutional networks. In International Conference on Learning Representations. find
  45. Shijie Wang, Wenqi Fan, Yue Feng, Lin Shanru, Xinyu Ma, Shuaiqiang Wang, and Dawei Yin. 2025. Knowledge graph retrieval-augmented generation for LLM-based recommendation. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 27152–…
  46. Xiaozhi Wang, Tianyu Gao, Zhaocheng Zhu, Zhengyan Zhang, Zhiyuan Liu, Juanzi Li, and Jian Tang. 2021. KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation. Transactions of the Association for Computational Linguistics, 9:176–194. find
  47. Yanbin Wei, Qiushi Huang, Yu Zhang, and James Kwok. 2023. KICGPT: Large language model with knowledge in context for knowledge graph completion. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 8667–8683, Singapore. Association for Computational Linguistics. find
  48. Derong Xu, Ziheng Zhang, Zhenxi Lin, Xian Wu, Zhihong Zhu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, and Enhong Chen. 2024. Multi-perspective improvement of knowledge graph completion with large language models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Langu… find
  49. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, and 43 others. 2024. Qwen2 technical report. Preprint, arXiv:240… find
  50. Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. 2015. Embedding entities and relations for learning and inference in knowledge bases. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings.
  51. Mengxue Yang, Chun Yang, Jiaqi Zhu, Jiafan Li, Jingqi Zhang, Yuyang Li, and Ying Li. 2025. SLiNT: Structure-aware language model with injection and contrastive training for knowledge graph completion. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 13658–13671, Suzhou… find
  52. Liang Yao, Chengsheng Mao, and Yuan Luo. 2019. Kg-bert: Bert for knowledge graph completion. find
  53. Yichi Zhang, Zhuo Chen, Lingbing Guo, yajing Xu, Wen Zhang, and Huajun Chen. 2024. Making large language models perform better in knowledge graph completion. In ACM Multimedia 2024. find
  54. Yongqi Zhang and Quanming Yao. 2022. Knowledge graph reasoning with relational digraph. In Proceedings of the ACM Web Conference 2022, WWW ’22, page 912–924, New York, NY, USA. Association for Computing Machinery. find
  55. Yunxiang Zhao, Jianzhong Qi, Qingwei Liu, and Rui Zhang. 2021. Wgcn: Graph convolutional networks with weighted structural features. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’21, page 624–633, New York, NY, USA. Associa… find
  56. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Preprint, arXiv:2306.05685.
  57. Jie Zhou, Ganqu Cui, Shengding Hu, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Lifeng Wang, Changcheng Li, and Maosong Sun. 2020. Graph neural networks: A review of methods and applications. AI Open, 1:57–81. find
  58. Zhaocheng Zhu, Xinyu Yuan, Michael Galkin, Louis-Pascal Xhonneux, Ming Zhang, Maxime Gazeau, and Jian Tang. 2023. Aast net: A scalable path-based reasoning approach for knowledge graphs. In Advances in Neural Information Processing Systems, volume 36, pages 59323–59336. Curran Associates, Inc. find
  59. Zhaocheng Zhu, Zuobai Zhang, Louis-Pascal Xhonneux, and Jian Tang. 2021. Neural bellman-ford networks: A general graph neural network framework for link prediction. In Advances in Neural Information Processing Systems, volume 34.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xie-2026-gs-quant-granular-semantic-generative/