KGE

Papers with KGE

Thesis Proposal: Uncertainty in Knowledge Graph Embeddings (2025.naacl-srw)

Copied to clipboard

Challenge:	Knowledge graph embedding (KGE) methods map entities and relations from knowledge graphs into numerical vector spaces.
Approach:	They propose to investigate various types of uncertainty in knowledge graph embedding methods and explore strategies to quantify, mitigate, and reason under uncertainty effectively.
Outcome:	The proposed methods have shown to be reliable in high-stakes domains and provide greater confidence in their use beyond benchmark datasets.

CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge (2022.acl-demo)

Copied to clipboard

Zhuoran Jin, Tianyi Men, Hongbang Yuan, Zhitao He, Dianbo Sui, Chenhao Wang, Zhipeng Xue, Yubo Chen, Jun Zhao

Semantic Text Processing

Challenge:	Existing methods focus on entity-centric knowledge, but CogKGE supports heterogeneous knowledge.
Approach:	They propose a knowledge graph embedding toolkit to represent multi-source and heterogeneous knowledge.
Outcome:	The proposed toolkit provides a unified programming framework for KGE tasks and a series of knowledge representations for downstream tasks.

Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction (2024.findings-emnlp)

Copied to clipboard

Yuqicheng Zhu, Nico Potyka, Mojtaba Nayyeri, Bo Xiong, Yunjie He, Evgeny Kharlamov, Steffen Staab

Semantic Text Processing

Challenge:	Knowledge graph embeddings (KGE) models are often used to predict missing links for knowledge graphs (KGs) however, multiple KG embedds can give conflicting predictions for unseen queries.
Approach:	They define predictive multiplicity in link prediction and introduce evaluation metrics to measure it using commonly used benchmark datasets.
Outcome:	The proposed methods significantly mitigat conflicts by 66% to 78% in link prediction.

Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models (2020.findings-emnlp)

Copied to clipboard

Zhiyuan Zhang, Xiaoqian Liu, Yi Zhang, Qi Su, Xu Sun, Bin He

Semantic Text Processing

Challenge:	Existing knowledge graph embedding models suffer from limited knowledge representation due to sparse and noisy dataset annotations.
Approach:	They propose to use pretrained language models to enhance knowledge representation by leveraging world knowledge from pretrained models.
Outcome:	Extensive experiments show that the proposed framework can improve results over existing models.

Conformalized Answer Set Prediction for Knowledge Graph Embedding (2025.naacl-long)

Copied to clipboard

Yuqicheng Zhu, Nico Potyka, Jiarong Pan, Bo Xiong, Yunjie He, Evgeny Kharlamov, Steffen Staab

Semantic Text Processing

Challenge:	Knowledge graph embeddings (KGE) map entities and predicates into numerical vectors, providing non-classical reasoning capabilities based on similarities and analogies between entities and relations.
Approach:	They propose to use knowledge graph embeddings to provide non-classical reasoning capabilities by exploiting similarities and analogies between entities and relations.
Outcome:	The proposed model can generate answer sets with probabilistic guarantees on four benchmark datasets and is scaled well with respect to the difficulty of the query.

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings (2021.findings-emnlp)

Copied to clipboard

Kai Wang, Yu Liu, Dan Lin, Michael Sheng

Semantic Text Processing

Challenge:	Recent knowledge graph embedding models based on hyperbolic geometry are complicated than Euclidean operations.
Approach:	They propose to use hyperbolic geometry to generate high-fidelity and parsimonious representations of hierarchical patterns in knowledge graphs.
Outcome:	The proposed models achieve state-of-the-art performance on two widely-used datasets and cost less than RotH.

Food Knowledge Representation Learning with Adversarial Substitution (2022.aacl-main)

Copied to clipboard

Diya Li, Mohammed J Zaki

Semantic Text Processing

Challenge:	Knowledge graph embedding (KGE) has been well-studied in general domains, but has not been examined for food computing.
Approach:	They propose to use a pre-trained language model to encode entities and relations, emphasizing contextual information in food KGs.
Outcome:	The proposed method is able to generate high quality substitutions over a food knowledge graph and provide generalized substitutions to meet different user needs.

TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation (2022.findings-emnlp)

Copied to clipboard

Xuanyu Zhang, Qing Yang, Dongliang Xu

Semantic Text Processing

Challenge:	Knowledge graph embedding (KGE) is a computational approach to learn continuous vector representations of relations and entities in knowledge graphs.
Approach:	They propose a transition-based method to learn continuous vector representations of relations and entities in knowledge graph (KG) it replaces a single relation vector in the relation part with a synthetic relation representation with entity-relation interactions to solve these problems.
Outcome:	The proposed method achieves state-of-the-art on a large knowledge graph dataset.

Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs (2023.emnlp-main)

Copied to clipboard

Simone Conia, Min Li, Daniel Lee, Umar Minhas, Ihab Ilyas, Yunyao Li

Multimodality

Challenge:	Existing methods to generate knowledge graphs are unable to handle non-English textual information.
Approach:	They propose a task of automatic Knowledge Graph Completion to bridge the gap between English and non-English textual information.
Outcome:	The proposed method bridges the gap between the quantity and quality of textual information between English and non-English languages.

AutoETER: Automated Entity Type Representation for Knowledge Graph Embedding (2020.findings-emnlp)

Copied to clipboard

Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu, Jingyang Li

Semantic Text Processing

Challenge:	Existing knowledge graphs are incomplete whether they are constructed manually or automatically, limiting the effectiveness when exploited for downstream applications.
Approach:	They propose a KGE framework with an automatic type embedding mechanism which can be easily integrated into any existing KGE model.
Outcome:	The proposed model can model and infer all the relation patterns and complex relations compared to state-of-the-art models on four datasets.

Learning Low-dimensional Multi-domain Knowledge Graph Embedding via Dual Archimedean Spirals (2024.findings-acl)

Copied to clipboard

Jiang Li, Xiangdong Su, Fujun Zhang, Guanglai Gao

Semantic Text Processing

Challenge:	Existing knowledge graph embedding methods make domain constraints on embeddable domains, leading to poor performance.
Approach:	They propose a low-dimensional KGE model for multi-domain knowledge graphs that embeds domains and domains by regularization function.
Outcome:	The proposed model can distinguish entities from domains by encoding the same relation on the same archimedean spiral.

Perform like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference (2022.coling-1)

Copied to clipboard

Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu

Semantic Text Processing

Challenge:	Existing knowledge graphs are incomplete and therefore lack interpretability.
Approach:	They propose a closed-loop neural-symbolic learning framework EngineKG to address the natural incompleteness of knowledge graphs.
Outcome:	The proposed model outperforms baselines on link prediction tasks on four real-world datasets.

RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding (2021.eacl-main)

Copied to clipboard

Danushka Bollegala, Huda Hakami, Yuichi Yoshida, Ken-ichi Kawarabayashi

Semantic Text Processing

Challenge:	Existing methods for embedding entities and relations in knowledge graphs are heuristically motivated and theoretical understanding of such embeddables is underdeveloped.
Approach:	They extend the random walk model of word embeddings to Knowledge Graph Embeddings (KGEs) they propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph.
Outcome:	The proposed learning objective is motivated by the theoretical analysis to learn KGEs from a given knowledge graph.

Poisoning Knowledge Graph Embeddings via Relation Inference Patterns (2021.acl-long)

Copied to clipboard

Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O’Sullivan

Semantic Text Processing

Challenge:	Knowledge graph embeddings (KGE) models are increasingly deployed in domains with high stake decision making where it is critical to identify the potential security vulnerabilities that might cause failure.
Approach:	They propose to exploit the inductive abilities of knowledge graph embedding models by crafting adversarial additions that can improve model’s confidence on decoy facts.
Outcome:	The proposed attacks outperform state-of-the-art baselines on four KGE models for two publicly available datasets and generalize across all model-dataset combinations.

Random Entity Quantization for Parameter-Efficient Compositional Knowledge Graph Representation (2023.emnlp-main)

Copied to clipboard

Jiaang Li, Quan Wang, Yi Liu, Licheng Zhang, Zhendong Mao

Semantic Text Processing

Challenge:	Existing approaches to learning on Knowledge Graphs (KGs) are not critical for learning on KGs.
Approach:	They propose an alternative approach to represent entities by composing entity-corresponding codewords matched from predefined small-scale codebooks.
Outcome:	The proposed approach achieves similar results to existing methods.

Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis (2021.naacl-main)

Copied to clipboard

Xutan Peng, Guanyi Chen, Chenghua Lin, Mark Stevenson

Semantic Text Processing

Challenge:	Knowledge Graph Embeddings (KGEs) have been explored in recent years due to their promise for a wide range of applications.
Approach:	They propose a KGE framework which can reduce the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches.
Outcome:	The proposed framework reduces the training time and carbon footprint by orders of magnitudes compared with state-of-the-art approaches while producing competitive performance.

Decoupling Mixture-of-Graphs: Unseen Relational Learning for Knowledge Graph Completion by Fusing Ontology and Textual Experts (2022.coling-1)

Copied to clipboard

Ran Song, Shizhu He, Suncong Zheng, Shengxiang Gao, Kang Liu, Zhengtao Yu, Jun Zhao

Semantic Text Processing

Challenge:	Existing methods for knowledge Graph Completion (KGC) fail in unseen relation representations.
Approach:	They propose to use three kinds of graphs to obtain unseen relation representations . they propose to decouple mixture-of-graph experts (DMoG) for unseened relations learning .
Outcome:	The proposed method outperforms the state-of-the-art methods on unseen relation representations.

Sequence-to-Sequence Knowledge Graph Completion and Question Answering (2022.acl-long)

Copied to clipboard

Apoorv Saxena, Adrian Kochsiek, Rainer Gemulla

Semantic Text Processing

Challenge:	Knowledge graph embedding (KGE) models represent each entity and relation of a knowledge graph (KG) with low-dimensional embeddable vectors.
Approach:	They propose to use an off-the-shelf encoder-decoder Transformer model to generate a knowledge graph embedding model that can be used for KG link prediction and incomplete KG question answering.
Outcome:	The proposed model outperforms baselines on multiple large-scale datasets without extensive hyperparameter tuning.

CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion (2022.acl-long)

Copied to clipboard

Guanglin Niu, Bo Li, Yongfei Zhang, Shiliang Pu

Semantic Text Processing

Challenge:	Existing knowledge graph embedding techniques rely on fact-view data to predict missing links between entities, limiting their performance.
Approach:	They propose a commonsense-aware knowledge embedding framework which generates commonsensense from factual triples with entity concepts for a KGC task.
Outcome:	The proposed framework could produce high-quality negative triples and joint commonsense and fact-view link prediction.

Learning to Borrow– Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph Completion (2022.naacl-main)

Copied to clipboard

Huda Hakami, Mona Hakami, Angrosh Mandya, Danushka Bollegala

Semantic Text Processing

Challenge:	Existing methods to integrate text corpora with knowledge graphs (KGs) have been effective in various NLP tasks such as analyzing and predicting relationships between entities.
Approach:	They propose a method that borrows LDPs from entities that co-occur in sentences to represent entities that do not co-exist in a single sentence.
Outcome:	The proposed method improves the performance of prior methods such as TransE, DistMult, ComplEx and RotatE.

Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)

Copied to clipboard

Yuqicheng Zhu, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Evgeny Kharlamov, Steffen Staab

Semantic Text Processing

Challenge:	Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain.
Approach:	They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.
Outcome:	The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets.

KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings (2022.coling-1)

Copied to clipboard

Zhiping Luo, Wentao Xu, Weiqing Liu, Jiang Bian, Jian Yin, Tie-Yan Liu

Semantic Text Processing

Challenge:	Existing knowledge graph embedding methods ignore semantic similarity between related entities and entity-relation couples in different triples .
Approach:	They propose a contrastive learning framework for tensor decomposition based (TDB) KGE that can shorten the semantic distance of related entities and entity-relation couples in different triples and thus improve the performance of KGE.
Outcome:	The proposed method achieves 51.2% MRR, 46.8% Hits@1 on three standard KGE datasets, 37.8% MRR and 28.6% Hits @1 on FB15k-237 datasets and 59.1% MRR .

A Non-commutative Bilinear Model for Answering Path Queries in Knowledge Graphs (D19-1)

Copied to clipboard

Katsuhiko Hayashi, Masashi Shimbo

Structured Data in NLP

Challenge:	Knowledge graph embedding (KGE) is a promising approach to knowledge graph completion.
Approach:	They propose a bilinear KGE model based on block circulant matrices that is non-commutative and can be modeled by matrix product.
Outcome:	The proposed model can be used to model composite relations on a spectrum from diagonal to full relation matrices.

Hyperbolic Hierarchy-Aware Knowledge Graph Embedding for Link Prediction (2021.findings-emnlp)

Copied to clipboard

Zhe Pan, Peng Wang

Semantic Text Processing

Challenge:	Existing knowledge graph embedding methods are built on Euclidean space, which are difficult to handle hierarchical structures.
Approach:	They propose a KGE model with extended Poincaré Ball and polar coordinate system to capture hierarchical structures.
Outcome:	The proposed model captures hierarchical relationships with extended Poincaré Ball and polar coordinate system in hyperbolic space and achieves state-of-the-art results on part of link prediction tasks.

RulE: Knowledge Graph Reasoning with Rule Embedding (2024.findings-acl)

Copied to clipboard

Xiaojuan Tang, Song-Chun Zhu, Yitao Liang, Muhan Zhang

Semantic Text Processing

Challenge:	Knowledge graph reasoning is an important problem for knowledge graphs.
Approach:	They propose a framework that leverages logical rules to enhance KG reasoning by learning rule embeddings from existing triplets and first-order rules.
Outcome:	The proposed framework outperforms existing embedding-based and rule-based methods on multiple benchmarks.

DTDES-KGE: Dual-Teacher Knowledge Distillation with Distinct Embedding Spaces for Knowledge Graph Embeddings (2025.findings-emnlp)

Copied to clipboard

Bofan Wei, Hongyuan Xu, Yuhang Niu, Jiarui Ren, Yanlong Wen, Xiaojie Yuan

Semantic Text Processing

Challenge:	Existing knowledge distillation methods rely on a single teacher embedding space . existing methods overlook valuable complementary knowledge from teachers in distinct embeddable spaces.
Approach:	They propose a knowledge distillation framework that leverages dual teachers in embedding spaces to enhance performance.
Outcome:	The proposed framework significantly improves knowledge distillation performance by leveraging dual teachers in distinct embedding spaces.

Enhancing Hyperbolic Knowledge Graph Embeddings via Lorentz Transformations (2024.findings-acl)

Copied to clipboard

Xiran Fan, Minghua Xu, Huiyuan Chen, Yuzhong Chen, Mahashweta Das, Hao Yang

Semantic Text Processing

Challenge:	Existing methods for knowledge graph embedding rely on tangent approximation and are not fully hyperbolic.
Approach:	They propose a fully hyperbolic KGE method that represents entities as points in the Lorentz model and represents relations as the intrinsic transformation.
Outcome:	The proposed method captures various types of relations including hierarchical structures.

Knowledge Graph Embedding with Hierarchical Relation Structure (D18-1)

Copied to clipboard

Zhao Zhang, Fuzhen Zhuang, Meng Qu, Fen Lin, Qing He

Semantic Text Processing

Challenge:	Existing knowledge graph embedding models embed entities and relations into latent vectors without leveraging rich information from relation structure.
Approach:	They extend existing KGE models to learn knowledge representations by leveraging relation structure . authors say their approach is capable of extending other KGEs .
Outcome:	The proposed approach can extend existing KGE models, and validates against baselines.

Knowledge Graph Pooling and Unpooling for Concept Abstraction (2025.coling-main)

Copied to clipboard

Juan Li, Wen Zhang, Zhiqiang Liu, Mingchen Tu, Mingyang Chen, Ningyu Zhang, Shijian Li

Structured Data in NLP

Challenge:	Knowledge graph embedding (KGE) aims to embed entities and relations as vectors in a continuous space.
Approach:	They propose a framework with KG Pooling and unpooling and Contrastive Learning to abstract and encode latent concepts for better KG prediction.
Outcome:	The proposed framework outperforms baselines on link prediction task.

Compounding Geometric Operations for Knowledge Graph Completion (2023.acl-long)

Copied to clipboard

Xiou Ge, Yun Cheng Wang, Bin Wang, C.-C. Jay Kuo

Structured Data in NLP

Challenge:	Knowledge graph embedding (KGE) is one of the most fundamental problems in AI research.
Approach:	They propose a new knowledge graph embedding model by leveraging translation, rotation, and scaling operations to form a composite one.
Outcome:	The proposed model outperforms existing models on three KG prediction tasks.

ReInceptionE: Relation-Aware Inception Network with Joint Local-Global Structural Information for Knowledge Graph Embedding (2020.acl-main)

Copied to clipboard

Zhiwen Xie, Guangyou Zhou, Jin Liu, Jimmy Xiangji Huang

Semantic Text Processing

Challenge:	Existing knowledge graph embedding methods are limited in their expressiveness and lack structural information in the embeddable space.
Approach:	They propose to use a relation-aware network to learn query embedding . they first explore the Inception network to further increase interactions between head and relation embedders .
Outcome:	The proposed network improves performance on WN18RR and FB15k-237 datasets.

MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding (2024.emnlp-main)

Copied to clipboard

Yang Liu, Huang Fang, Yunfeng Cai, Mingming Sun

Semantic Text Processing

Challenge:	Existing knowledge graph embedding models suffer from Z-paradox, a deficiency in expressiveness . Embedding-based models map each entity and relation into a vector or matrix .
Approach:	They propose a new knowledge graph embedding model that does not suffer from Z-paradox while preserves strong expressiveness to model various relation patterns with theoretical justification.
Outcome:	The proposed model outperforms existing models on link prediction tasks while maintaining strong expressiveness.

Croppable Knowledge Graph Embedding (2025.acl-long)

Copied to clipboard

Yushan Zhu, Wen Zhang, Zhiqiang Liu, Mingyang Chen, Lei Liang, Huajun Chen

Semantic Text Processing

Challenge:	Knowledge Graph Embedding (KGE) is a common approach for Knowledge Grasse (KGs) in AI tasks.
Approach:	They propose a new KGE training framework MED that allows one training to obtain a croppable KGE model for multiple scenarios with different dimensional needs.
Outcome:	The proposed framework improves low-dimensional sub-models and makes high-dimensional models retain the low-dimension sub-modells’ capacity.

RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge Graph (2025.acl-long)

Copied to clipboard

Junsik Kim, Jinwook Park, Kangil Kim

Semantic Text Processing

Challenge:	Knowledge graph embeddings suffer from incompleteness, a problem that is often overlooked . a generalized plug-in approach to SFBR disrupts consistency by concentrating embeddables under entity-based regularization .
Approach:	They propose a plug-in KGE method that uses relation specific entity transformation to enhance semantic consistency.
Outcome:	The proposed method outperforms state-of-the-art methods in knowledge graph embedding tasks . the proposed method is based on a plug-in approach that disrupts consistency .

Should We Use a Fixed Embedding Size? Customized Dimension Sizes for Knowledge Graph Embedding (2025.coling-main)

Copied to clipboard

Zhanpeng Guan, Zhao Zhang, Yiqing Wu, Fuwei Zhang, Yongjun Xu

Semantic Text Processing

Challenge:	Knowledge Graph Embedding (KGE) aims to project entities and relations into a low-dimensional space, which is crucial for knowledge completion, fusion, and inference.
Approach:	They propose to embed entities and relations into a low-dimensional space to enable knowledge Graphs to be effectively used by downstream AI tasks.
Outcome:	The proposed framework is universal and flexible, suitable for various KGE models.

KG-TRICK: Unifying Textual and Relational Information Completion of Knowledge for Multilingual Knowledge Graphs (2025.coling-main)

Copied to clipboard

Zelin Zhou, Simone Conia, Daniel Lee, Min Li, Shenglei Huang, Umar Farooq Minhas, Saloni Potdar, Henry Xiao, Yunyao Li

Knowledge Representation

Challenge:	Existing studies have shown that combining information from KGs in different languages aids knowledge Graph Completion and Knowledge Graph Enhancement.
Approach:	They propose a sequence-to-sequence framework that unifies tasks of textual and relational information completion for multilingual knowledge graphs.
Outcome:	The proposed framework unifies tasks of KGC and KGE into a single framework.

Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Zijie Huang, Daheng Wang, Binxuan Huang, Chenwei Zhang, Jingbo Shang, Yan Liang, Zhengyang Wang, Xian Li, Christos Faloutsos, Yizhou Sun, Wei Wang

Semantic Text Processing

Challenge:	Existing methods to embed knowledge graphs have ignored the fact that they contain two fundamentally different views: high-level ontology-view concepts and fine-grained instance-view entities.
Approach:	They propose a novel geometric representation that jointly embeds the two views of a KG using dual geometric representations.
Outcome:	Experiments on the public DBpedia KG and a newly-created industrial KG show the proposed method works well.

Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods (2021.emnlp-main)

Copied to clipboard

Peru Bhardwaj, John Kelleher, Luca Costabello, Declan O’Sullivan

Semantic Text Processing

Challenge:	Knowledge Graph Embeddings (KGE) are widely used for relational learning on large scale Knowledge . however, little is known about the security vulnerabilities that might disrupt their intended behaviour.
Approach:	They propose to use model-agnostic instance attribution methods to select adversarial deletions and a heuristic method to replace one of the two entities in each influential triple to generate adversarials.
Outcome:	The proposed methods outperform the state-of-the-art data poisoning attacks on KGE models and improve the MRR degradation by up to 62% over the baselines.

BiQUE: Biquaternionic Embeddings of Knowledge Graphs (2021.emnlp-main)

Copied to clipboard

Jia Guo, Stanley Kok

Semantic Text Processing

Challenge:	Existing knowledge graph embeddings rely on geometric operations to model relational patterns such as symmetry and hierarchical semantics.
Approach:	They propose a new knowledge graph embedding model that integrates multiple geometric transformations to model multi-relational knowledge graphs.
Outcome:	Experiments on five datasets show that BiQUE can model symmetry, inversion, and composition.

Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction (2020.emnlp-main)

Copied to clipboard

Tara Safavi, Danai Koutra, Edgar Meij

Semantic Text Processing

Challenge:	Existing calibration techniques are less effective under the standard closed-world assumption (CWA) and the more realistic open-world hypothesis (OWA) Existing methods are not effective under OWA and provide explanations for this discrepancy.
Approach:	They conduct an evaluation under the standard closed-world assumption (CWA) and introduce the more realistic but challenging open-world assume (OWA) . they find existing calibration techniques are much less effective under the OWA than the CWA .
Outcome:	The proposed calibration techniques are much less effective under the open-world assumption (OWA) and explain the discrepancy.

Knowledge Graph Representation Learning using Ordinary Differential Equations (2021.emnlp-main)

Copied to clipboard

Mojtaba Nayyeri, Chengjin Xu, Franca Hoffmann, Mirza Mohtashim Alam, Jens Lehmann, Sahar Vahdati

Semantic Text Processing

Challenge:	Knowledge Graph Embeddings (KGEs) map entities and relations from knowledge graphs into a geometric space.
Approach:	They propose a neuro differential KGE that embeds nodes of a KG on the trajectories of Ordinary Differential Equations (ODEs) they represent each relation (edge) in a knowledge graph as a vector field on several manifolds.
Outcome:	The proposed model can preserve graph characteristics including structural aspects and semantics and avoid wrong inferences.

From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposing (2025.findings-emnlp)

Copied to clipboard

Chengrui Xiang, Tengfei Ma, Xiangzheng Fu, Yiping Liu, Bosheng Song, Xiangxiang Zeng

Semantic Text Processing

Challenge:	Existing methods for drug repurposing ignore common-sense biomedical concept knowledge in real-world labs, such as mechanistic priors indicating that certain drugs are fundamentally incompatible with specific treatments.
Approach:	They propose a Large Language Model-assisted framework for Drug Repurposing which improves the representation of biomedical concepts within KGs.
Outcome:	The proposed framework improves the representation of biomedical concepts within KGs by extracting treatment-related textual representations of biomedic entities from large language models and fine-tuning knowledge graph embedding models.

UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference (2021.emnlp-main)

Copied to clipboard

Kewei Cheng, Ziqing Yang, Ming Zhang, Yizhou Sun

Structured Data in NLP

Challenge:	Knowledge graph inference has been studied extensively due to its wide applications.
Approach:	They propose a framework that restricts logical rules to be definite Horn rules and can exploit the knowledge in logical rule-based reasoning and KGE in an extremely efficient way.
Outcome:	The proposed framework can exploit the knowledge in logical rules and improve KGE in an extremely efficient way.

SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrast (2025.findings-emnlp)

Copied to clipboard

Jiashi Lin, Changhong Jiang, Yixiao Wang, Xinyi Zhu, Zhongtian Hu, Wei Zhang

Semantic Text Processing

Challenge:	Existing knowledge Graph Embedding approaches lack structural semantics of knowledge graphs . structure-aware calibration (SaCa) is a framework designed to calibrate KGEs based on global structural patterns.
Approach:	a new framework is designed to calibrate knowledge graphs using global structural patterns.
Outcome:	a new framework can calibrate KGE models using global structural patterns . the framework consistently boosts performance across ten models on link prediction and entity classification tasks .

Knowledge GeoGebra: Leveraging Geometry of Relation Embeddings in Knowledge Graph Completion (2024.lrec-main)

Copied to clipboard

Kossi Amouzouvi, Bowen Song, Sahar Vahdati, Jens Lehmann

Semantic Text Processing

Challenge:	Knowledge graph embedding models are limited to the algebra and geometry of the entity embeddable space, the algebra of the relation embeddible space, and the interaction between relation and entity embeds.
Approach:	They propose a method that leverages the geometry of relation embeddings and generalizes it with the concept of a butterfly curve, consecutively.
Outcome:	The proposed model outperforms existing models on the WN18RR, FB15K-237 and YouTube benchmarks.

Block-Diagonal Orthogonal Relation and Matrix Entity for Knowledge Graph Embedding (2024.findings-emnlp)

Copied to clipboard

Yihua Zhu, Hidetoshi Shimodaira

Semantic Text Processing

Challenge:	Existing knowledge graph embeddings (KGs) are limited in their flexibility and difficulties in generalizing them for higher-dimensional rotations.
Approach:	They propose a KGE model employing matrices for entities and block-diagonal orthogonal matrics with Riemannian optimization for relations that captures several relation patterns that rotation-based methods can identify.
Outcome:	The proposed model outperforms state-of-the-art models while reducing the number of relation parameters.

A Mutual Information Perspective on Knowledge Graph Embedding (2025.acl-long)

Copied to clipboard

Jiang Li, Xiangdong Su, Zehua Duo, Tian Lan, Xiaotao Guo, Guanglai Gao

Semantic Text Processing

Challenge:	Existing knowledge graph embedding techniques suffer from high intra-group similarity, loss of semantic information, and insufficient inference capability, particularly in complex relation patterns such as 1-N and N-1 relations.
Approach:	They propose a knowledge graph embedding framework that leverages mutual information maximization to improve the semantic representation of entities and relations.
Outcome:	Extensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method, with consistent performance improvements across various baseline models.

Self-Knowledge Distillation for Knowledge Graph Embedding (2024.lrec-main)

Copied to clipboard

Haotian Xu, Yuhua Wang, Jiahui Fan

Semantic Text Processing

Challenge:	Knowledge graph embedding (KGE) is an important task for many downstream applications.
Approach:	They propose to use self-knowledge distillation to learn a low-dimensional model from a pre-trained high-dimensional one.
Outcome:	The proposed model can improve model performance while maintaining lightweight structure.

KGE Calibrator: An Efficient Probability Calibration Method of Knowledge Graph Embedding Models for Trustworthy Link Prediction (2025.emnlp-main)

Copied to clipboard

Yang Yang, Mohan Timilsina, Edward Curry

Semantic Text Processing

Challenge:	Existing methods for probability calibration of knowledge graph embedding models are ill-suited for KGEs.
Approach:	They propose a method to calibrate knowledge graph embedding models for ranking-based link prediction using a Jump Selection Strategy and Multi-Binning Scaling to enhance reliability.
Outcome:	Experiments show that the KGEC outperforms existing calibration methods in terms of effectiveness and efficiency.