Effective negative triplet sampling for knowledge graph embedding

Khobragade, Anish; Mahajan, Rushikesh; Langi, Hrithik; Mundhe, Rohit; Ghumbre, Shashikant

doi:10.1080/02522667.2022.2133215

Cited by 5 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, n=|B′t| be the number of negative triplets generated through uniformly replacing either the head or tail (not both) of each positive triplet by any other entity e i ∈ E , expressed in equation (3): Therefore, Bt′={b′o,b′1,…,b′n}, where contaminated triplet ∀bi=(h′i,rk,t′j)∉Tl. The updated NS caching method (Khobragade et al , 2022) creates a negative triplet for every positive one using equation (4). A score function of the respective embedding method (mentioned in Table 1) is used to select the best negative triplets.…”

Section: Methodsmentioning

confidence: 99%

Infer the missing facts of D3FEND using knowledge graph representation learning

Khobragade

Ghumbre²,

Pachghare

2023

IJWIS

Self Cite

View full text Add to dashboard Cite

Purpose MITRE and the National Security Agency cooperatively developed and maintained a D3FEND knowledge graph (KG). It provides concepts as an entity from the cybersecurity countermeasure domain, such as dynamic, emulated and file analysis. Those entities are linked by applying relationships such as analyze, may_contains and encrypt. A fundamental challenge for collaborative designers is to encode knowledge and efficiently interrelate the cyber-domain facts generated daily. However, the designers manually update the graph contents with new or missing facts to enrich the knowledge. This paper aims to propose an automated approach to predict the missing facts using the link prediction task, leveraging embedding as representation learning. Design/methodology/approach D3FEND is available in the resource description framework (RDF) format. In the preprocessing step, the facts in RDF format converted to subject–predicate–object triplet format contain 5,967 entities and 98 relationship types. Progressive distance-based, bilinear and convolutional embedding models are applied to learn the embeddings of entities and relations. This study presents a link prediction task to infer missing facts using learned embeddings. Findings Experimental results show that the translational model performs well on high-rank results, whereas the bilinear model is superior in capturing the latent semantics of complex relationship types. However, the convolutional model outperforms 44% of the true facts and achieves a 3% improvement in results compared to other models. Research limitations/implications Despite the success of embedding models to enrich D3FEND using link prediction under the supervised learning setup, it has some limitations, such as not capturing diversity and hierarchies of relations. The average node degree of D3FEND KG is 16.85, with 12% of entities having a node degree less than 2, especially there are many entities or relations with few or no observed links. This results in sparsity and data imbalance, which affect the model performance even after increasing the embedding vector size. Moreover, KG embedding models consider existing entities and relations and may not incorporate external or contextual information such as textual descriptions, temporal dynamics or domain knowledge, which can enhance the link prediction performance. Practical implications Link prediction in the D3FEND KG can benefit cybersecurity countermeasure strategies in several ways, such as it can help to identify gaps or weaknesses in the existing defensive methods and suggest possible ways to improve or augment them; it can help to compare and contrast different defensive methods and understand their trade-offs and synergies; it can help to discover novel or emerging defensive methods by inferring new relations from existing data or external sources; and it can help to generate recommendations or guidance for selecting or deploying appropriate defensive methods based on the characteristics and objectives of the system or network. Originality/value The representation learning approach helps to reduce incompleteness using a link prediction that infers possible missing facts by using the existing entities and relations of D3FEND.

show abstract

Section: Methodsmentioning

confidence: 99%

Infer the missing facts of D3FEND using knowledge graph representation learning

Khobragade

Ghumbre²,

Pachghare

2023

IJWIS

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the second paper (Khobragade et al , 2023) entitled, “Infer the missing facts of D3FEND using knowledge graph representation learning” by Khobragade et al, the authors proposed an automated approach to predict the missing facts using the link prediction task, leveraging embedding as representation learning. Experimental results show that the translational model performs well on high-rank results, whereas the bilinear model is superior in capturing the latent semantics of complex relationship types.…”

mentioning

confidence: 99%

Guest editorial: Current trends in semantic web and knowledge graphs

Tiwari,

Ortiz-Rodriguez,

Villazon

2023

IJWIS

View full text Add to dashboard Cite

Knowledge graphs are considered as a set of data points associated with relations to describe the domains such as an organization, business or academics. They have a potential role to bridge the semantic gap between unstructured and structured information and foster new research directions and tasks with new possibilities to represent, query, visualize, interact and make more understandable information. Knowledge graphs are powerful in representing data in search and recommendation systems that explore new insights about the domain. Recently, knowledge graphs gained popularity with deep learning and graph embedding. This special issue has been organized to invite the extended version of the KGSWC-2022 conference accepted papers.This special issue aims to provide a forum for the semantic Web community, bringing together researchers and practitioners in the industry to share ideas about R and D projects and increasing the adoption of semantic Web technologies within the region. In total, nine papers were submitted to this special issue. After a rigorous review according to relevance, originality, technical novelties and presentation quality, we selected three manuscripts. A summary is outlined below.In the first paper (Payghode et al., 2023) entitled, "Object detection and activity recognition in video surveillance using neural networks" by Payghode et al., the authors develop a deep learning framework to automate the task of analyzing video footage through object detection in images by using the neural network. This paper provides an exhaustive comparison between the existing and the proposed methods. It has the highest object detection accuracy.In the second paper (Khobragade et al., 2023) entitled, "Infer the missing facts of D3FEND using knowledge graph representation learning" by Khobragade et al., the authors proposed an automated approach to predict the missing facts using the link prediction task, leveraging embedding as representation learning. Experimental results show that the translational model performs well on high-rank results, whereas the bilinear model is superior in capturing the latent semantics of complex relationship types. However, the convolutional model outperforms 44% of the facts and achieves a 3% improvement in results compared to other models.In the third paper (Hafidi et al., 2023) entitled, "Semantic Web and machine learning techniques addressing semantic interoperability in Industry 4.0" by Hafidi et al., the authors offered a comprehensive examination of the various solutions currently accessible for addressing the challenge of semantic interoperability in cyber-physical systems (CPS) and help to identify the most relevant points in the development of semantic models and machine learning solutions to the interoperability problem, and how these solutions are implemented in CPS.The guest editors would like to express their deep gratitude to all the authors who have submitted their valuable contributions and to the highly qualified anonymous reviewers. We think that the selected contrib...

show abstract