Position within the page tree

Home
Institute
Team
He, Yunjie

Yunjie He

Researcher
KI
Analytic Computing

Contact

+49 711 685 88126
Email

Universitätsstraße 32
70569 Stuttgart
Germany
Room: 2.312a

Publications

He, Y., Xiong, B., Hernández, D., Zhu, Y., Kharlamov, E., & Staab, S. (2025). DAGE: DAG Query Answering via Relational Combinator with Logical Constraints. THE WEB CONFERENCE 2025. https://openreview.net/forum?id=x1nXBzUknn
- BibTeX
- Link
BibTeX
@inproceedings{he2025dage, abstract = {Predicting answers to queries over knowledge graphs is called a complex reasoning task because answering a query requires subdividing it into subqueries. Existing query embedding methods use this decomposition to compute the embedding of a query as the combination of the embedding of the subqueries. This requirement limits the answerable queries to queries having a single free variable and being decomposable, which are called tree-form queries and correspond to the SROI^- description logic. In this paper, we define a more general set of queries, called DAG queries and formulated in the ALCOIR description logic, propose a query embedding method for them, called DAGE, and a new benchmark to evaluate query embeddings on them. Given the computational graph of a DAG query, DAGE combines the possibly multiple paths between two nodes into a single path with a trainable operator that represents the intersection of relations and learns DAG-DL from tautologies. We show that it is possible to implement DAGE on top of existing query embedding methods, and we empirically measure the improvement of our method over the results of vanilla methods evaluated in tree-form queries that approximate the DAG queries of our proposed benchmark.}, author = {He, Yunjie and Xiong, Bo and Hern{\'a}ndez, Daniel and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {THE WEB CONFERENCE 2025}, language = {en}, preprinturl = {https://doi.org/10.48550/arXiv.2410.22105}, publisher = {ACM}, title = {DAGE: DAG Query Answering via Relational Combinator with Logical Constraints}, url = {https://openreview.net/forum?id=x1nXBzUknn}, year = 2025 }
Link
https://openreview.net/forum?id=x1nXBzUknn
He, Y., Hernandez, D., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2024). Generating SROI^- Ontologies via Knowledge Graph Query Embedding Learning. ECAI 2024, 392, 4279–4286. https://doi.org/10.3233/FAIA241002
- BibTeX
- Link
BibTeX
@inproceedings{he2024generating, abstract = {Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of SROI− description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to SROI− description logic concepts. Every SROI− concept is embedded as a cone in complex vector space, and each SROI− relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn SROI− axioms, and defines an algebra whose operations correspond one-to-one to SROI− description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.}, author = {He, Yunjie and Hernandez, Daniel and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {ECAI 2024}, doi = {10.3233/FAIA241002}, isbn = {9781643685489}, issn = {1879-8314}, language = {en}, month = {10}, pages = {4279 - 4286}, publisher = {IOS Press}, title = {Generating SROI^{-} Ontologies via Knowledge Graph Query Embedding Learning}, type = {Publication}, url = {https://arxiv.org/abs/2407.09212}, volume = 392, year = 2024 }
Link
https://arxiv.org/abs/2407.09212
Potyka, N., Zhu, Y., He, Y., Kharlamov, E., & Staab, S. (2024). Robust Knowledge Extraction from Large Language Models using Social Choice Theory. In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems. https://arxiv.org/abs/2312.14877
- BibTeX
- Link
BibTeX
@inproceedings{noauthororeditor2023robust, abstract = {Large-language models (LLMs) have the potential to support a wide range of applications like conversational agents, creative writing, text improvement, and general query answering. However, they are ill-suited for query answering in high-stake domains like medicine because they generate answers at random and their answers are typically not robust - even the same query can result in different answers when prompted multiple times. In order to improve the robustness of LLM queries, we propose using ranking queries repeatedly and to aggregate the queries using methods from social choice theory. We study ranking queries in diagnostic settings like medical and fault diagnosis and discuss how the Partial Borda Choice function from the literature can be applied to merge multiple query results. We discuss some additional interesting properties in our setting and evaluate the robustness of our approach empirically.}, author = {Potyka, Nico and Zhu, Yuqicheng and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {In Proceedings of the 23rd International Conference on Autonomous Agents and Multi-Agent Systems}, title = {Robust Knowledge Extraction from Large Language Models using Social Choice Theory}, url = {https://arxiv.org/abs/2312.14877}, year = 2024 }
Link
https://arxiv.org/abs/2312.14877
He, Y., Nayyeri, M., Xiong, B., Zhu, Y., Kharlamov, E., & Staab, S. (2023). Can Pattern Learning Enhance Complex Logical Query Answering? In I. Fundulaki, K. Kozaki, D. Gariko, & J. M. Gomez-Perez (Eds.), ISWC-Posters-Demos-Industry 2023 : Posters, Demos, and Industry Tracks at ISWC 2023 (No. 3632; Issue 3632). RWTH Aachen. https://ceur-ws.org/Vol-3632/ISWC2023_paper_463.pdf
- BibTeX
- Link
BibTeX
@inproceedings{he2023pattern, address = {Aachen}, author = {He, Yunjie and Nayyeri, Mojtaba and Xiong, Bo and Zhu, Yuqicheng and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {ISWC-Posters-Demos-Industry 2023 : Posters, Demos, and Industry Tracks at ISWC 2023}, editor = {Fundulaki, Irini and Kozaki, Kouji and Gariko, Daniel and Gomez-Perez, Jose Manuel}, eventdate = {2023-11-06/2023-11-10}, eventtitle = {22nd International Semantic Web Conference (ISWC 2023)}, language = {eng}, number = 3632, publisher = {RWTH Aachen}, series = {CEUR Workshop Proceedings}, title = {Can Pattern Learning Enhance Complex Logical Query Answering?}, url = {https://ceur-ws.org/Vol-3632/ISWC2023_paper_463.pdf}, venue = {Athens, Greece}, year = 2023 }
Link
https://ceur-ws.org/Vol-3632/ISWC2023_paper_463.pdf
Potyka, N., Zhu, Y., He, Y., Kharlamov, E., & Staab, S. (2023). Robust Knowledge Extraction from Large Language Models using Social Choice Theory. AAMAS ’24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems. AAMAS ’24 : International Conference on Autonomous Agents and Multiagent Systems, Auckland, New Zealand.
- BibTeX
BibTeX
@inproceedings{potyka2023robust, address = {Richland}, author = {Potyka, Nico and Zhu, Yuqicheng and He, Yunjie and Kharlamov, Evgeny and Staab, Steffen}, booktitle = {AAMAS '24 : Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems}, eventdate = {2024-05-06/2024-05-10}, eventtitle = {AAMAS '24 : International Conference on Autonomous Agents and Multiagent Systems}, isbn = {979-8-4007-0486-4}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, title = {Robust Knowledge Extraction from Large Language Models using Social Choice Theory}, venue = {Auckland, New Zealand}, year = 2023 }

Teaching

Deep Learning Lab 2022/23 Winter Term

Yunjie He

Contact

Publications

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Teaching

Audience

Formalities

Services

Organization

Yunjie He

Contact

Publications

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Link

BibTeX

Teaching

Here you can reach us

Audience

Formalities

Services

Organization