Knowledge Graph Embedding With Iterative Guidance From Soft Rules

Guo, Shu; Wang, Quan; Wang, Lihong; Wang, Bin; Guo, Li

doi:10.1609/aaai.v32i1.11918

Cited by 136 publications

(59 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GPU DS also supports an arbitrary choice of subP instead of being determined by the number of GPUs. We conducted experiments on standard benchmark datasets of KG, including FB15K [6] , yago37 [22] , wikidata5m [23] , and Freebase86m [10] . FB15K and Freebase86m are subsets of the well-known knowledge base Freebase [24] with different scales.…”

Section: Gpu Dsmentioning

confidence: 99%

Efficient Knowledge Graph Embedding Training Framework with Multiple GPUs

Sun

Huang

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

When training a large-scale knowledge graph embedding (KGE) model with multiple graphics processing units (GPUs), the partition-based method is necessary for parallel training. However, existing partition-based training methods suffer from low GPU utilization and high input/output (IO) overhead between the memory and disk. For a high IO overhead between the disk and memory problem, we optimized the twice partitioning with fine-grained GPU scheduling to reduce the IO overhead between the CPU memory and disk. For low GPU utilization caused by the GPU load imbalance problem, we proposed balanced partitioning and dynamic scheduling methods to accelerate the training speed in different cases. With the above methods, we proposed fine-grained partitioning KGE, an efficient KGE training framework with multiple GPUs. We conducted experiments on some benchmarks of the knowledge graph, and the results show that our method achieves speedup compared to existing framework on the training of KGE.

show abstract

Section: Gpu Dsmentioning

confidence: 99%

Efficient Knowledge Graph Embedding Training Framework with Multiple GPUs

Sun

Huang

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In this way, the output ȳ ∈ R |C| is the product of f (I x ; θ) and the exponential of the sum of one-hot vectors from R weighted by their confidence scores. This PR integration gives a principled way to balance between rule constraints and faithfulness and has been proven effective in similar applications with logic rules (Guo et al 2018;Hu et al 2016).…”

Section: Knowledge Integrationmentioning

confidence: 99%

LOGICDEF: An Interpretable Defense Framework against Adversarial Examples via Inductive Scene Graph Reasoning

Yang

Kerce

Fekri

2022

AAAI

View full text Add to dashboard Cite

Deep vision models have provided new capability across a spectrum of applications in transportation, manufacturing, agriculture, commerce, and security. However, recent studies have demonstrated that these models are vulnerable to adversarial attack, exposing a risk-of-use in critical applications where untrusted parties have access to the data environment or even directly to the sensor inputs. Existing adversarial defense methods are either limited to specific types of attacks or are too complex to be applied to practical vision models. More importantly, these methods rely on techniques that are not interpretable to humans. In this work, we argue that an effective defense should produce an explanation as to why the system is attacked, and by using a representation that is easily readable by a human user, e.g. a logic formalism. To this end, we propose logic adversarial defense (LogicDef), a defense framework that utilizes the scene graph of the image to provide a contextual structure for detecting and explaining object classification. Our framework first mines inductive logic rules from the extracted scene graph, and then uses these rules to construct a defense model that alerts the user when the vision model violates the consistency rules. The defense model is interpretable and its robustness is further enhanced by incorporating existing relational commonsense knowledge from projects such as ConceptNet. In order to handle the hierarchical nature of such relational reasoning, we use a curriculum learning approach based on object taxonomy, yielding additional improvements to training and performance.

show abstract

“…Recently, many attempts (Chang et al, 2014, Liu, Wu, & Yang, 2017Minervini et al, 2017;Zhong et al, 2015Zhong et al, , 2017 have been made on incorporating extra information beyond KG triples. RUGE (Guo et al, 2018) uses AMIE+ (Galarraga et al, 2015) tool to extract soft rules from the training sets. The embeddings of entities and relations are learned from both labeled triples in a KG, and unlabeled triples whose labels need to be learned iteratively.…”

Section: Research Papermentioning

confidence: 99%

Learning Context-based Embeddings for Knowledge Graph Completion

Zhang

Feng

et al. 2022

Journal of Data and Information Science

View full text Add to dashboard Cite

Purpose Due to the incompleteness nature of knowledge graphs (KGs), the task of predicting missing links between entities becomes important. Many previous approaches are static, this posed a notable problem that all meanings of a polysemous entity share one embedding vector. This study aims to propose a polysemous embedding approach, named KG embedding under relational contexts (ContE for short), for missing link prediction. Design/methodology/approach ContE models and infers different relationship patterns by considering the context of the relationship, which is implicit in the local neighborhood of the relationship. The forward and backward impacts of the relationship in ContE are mapped to two different embedding vectors, which represent the contextual information of the relationship. Then, according to the position of the entity, the entity's polysemous representation is obtained by adding its static embedding vector to the corresponding context vector of the relationship. Findings ContE is a fully expressive, that is, given any ground truth over the triples, there are embedding assignments to entities and relations that can precisely separate the true triples from false ones. ContE is capable of modeling four connectivity patterns such as symmetry, antisymmetry, inversion and composition. Research limitations ContE needs to do a grid search to find best parameters to get best performance in practice, which is a time-consuming task. Sometimes, it requires longer entity vectors to get better performance than some other models. Practical implications ContE is a bilinear model, which is a quite simple model that could be applied to large-scale KGs. By considering contexts of relations, ContE can distinguish the exact meaning of an entity in different triples so that when performing compositional reasoning, it is capable to infer the connectivity patterns of relations and achieves good performance on link prediction tasks. Originality/value ContE considers the contexts of entities in terms of their positions in triples and the relationships they link to. It decomposes a relation vector into two vectors, namely, forward impact vector and backward impact vector in order to capture the relational contexts. ContE has the same low computational complexity as TransE. Therefore, it provides a new approach for contextualized knowledge graph embedding.

show abstract

Knowledge Graph Embedding With Iterative Guidance From Soft Rules

Cited by 136 publications

References 21 publications

Efficient Knowledge Graph Embedding Training Framework with Multiple GPUs

Efficient Knowledge Graph Embedding Training Framework with Multiple GPUs

LOGICDEF: An Interpretable Defense Framework against Adversarial Examples via Inductive Scene Graph Reasoning

Learning Context-based Embeddings for Knowledge Graph Completion

Contact Info

Product

Resources

About