Link Prediction on N-ary Relational Data

Guan, Saiping; Jin, Xiaolong; Wang, Yuanzhuo; Cheng, Xueqi

doi:10.1145/3308558.3313414

“…To preserve the whole expressivity of the KG, a set of new KGE-Methods are developed to directly operate on hypergraphs and hyper-relational graphs. Some of the methods that deal with hypergraphs are HEBE [52], HGE [157], Hyper2vec [59], HNN [36], HCN [154], DHNE [134], HHNE [9], Hyper-SAGNN [164], HypE [35] and methods that embedd hyper-relational graphs are for instance m-TransH [151], HSimple [35], RAE [163], GETD [84], TuckER [7], NaLP [51], HINGE [116], StarE [40].…”

Section: Kge-methods -Input Typementioning

confidence: 99%

A survey on visual transfer learning using knowledge graphs

Monka

¹

,

Halilaj

²

,

Rettinger

³

2022

View full text Add to dashboard Cite

The information perceived via visual observations of real-world phenomena is unstructured and complex. Computer vision (CV) is the field of research that attempts to make use of that information. Recent approaches of CV utilize deep learning (DL) methods as they perform quite well if training and testing domains follow the same underlying data distribution. However, it has been shown that minor variations in the images that occur when these methods are used in the real world can lead to unpredictable and catastrophic errors. Transfer learning is the area of machine learning that tries to prevent these errors. Especially, approaches that augment image data using auxiliary knowledge encoded in language embeddings or knowledge graphs (KGs) have achieved promising results in recent years. This survey focuses on visual transfer learning approaches using KGs, as we believe that KGs are well suited to store and represent any kind of auxiliary knowledge. KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding. Intending to enable the reader to solve visual transfer learning problems with the help of specific KG-DL configurations we start with a description of relevant modeling structures of a KG of various expressions, such as directed labeled graphs, hypergraphs, and hyper-relational graphs. We explain the notion of feature extractor, while specifically referring to visual and semantic features. We provide a broad overview of knowledge graph embedding methods and describe several joint training objectives suitable to combine them with high dimensional visual embeddings. The main section introduces four different categories on how a KG can be combined with a DL pipeline: 1) Knowledge Graph as a Reviewer; 2) Knowledge Graph as a Trainee; 3) Knowledge Graph as a Trainer; and 4) Knowledge Graph as a Peer. To help researchers find meaningful evaluation benchmarks, we provide an overview of generic KGs and a set of image processing datasets and benchmarks that include various types of auxiliary knowledge. Last, we summarize related surveys and give an outlook about challenges and open issues for future research.

show abstract

“…To preserve the whole expressivity of the KG, a set of new KGE-Methods are developed to directly operate on hypergraphs and hyper-relational graphs. Some of the methods that deal with hypergraphs are HEBE [34], HGE [35], Hyper2vec [36], HNN [37], HCN [38], DHNE [39], HHNE [40], Hyper-SAGNN [41], HypE [32] and methods that embedd hyper-relational graphs are for instance m-TransH [33], HSimple [32], RAE [42], GETD [43], TuckER [44], NaLP [45], HINGE [31], StarE [46].…”

Section: Visual Features Extractormentioning

confidence: 99%

A Survey on Visual Transfer Learning using Knowledge Graphs

Monka¹,

Halilaj²,

Rettinger³

2022

Preprint

View full text Add to dashboard Cite

The information perceived via visual observations of real-world phenomena is unstructured and complex. Computer vision (CV) is the field of research that attempts to make use of that information. Recent approaches of CV utilize deep learning (DL) methods as they perform quite well if training and testing domains follow the same underlying data distribution. However, it has been shown that minor variations in the images that occur when these methods are used in the real world can lead to unpredictable and catastrophic errors. Transfer learning is the area of machine learning that tries to prevent these errors. Especially, approaches that augment image data using auxiliary knowledge encoded in language embeddings or knowledge graphs (KGs) have achieved promising results in recent years. This survey focuses on visual transfer learning approaches using KGs, as we believe that KGs are well suited to store and represent any kind of auxiliary knowledge. KGs can represent auxiliary knowledge either in an underlying graph-structured schema or in a vector-based knowledge graph embedding. Intending to enable the reader to solve visual transfer learning problems with the help of specific KG-DL configurations we start with a description of relevant modeling structures of a KG of various expressions, such as directed labeled graphs, hypergraphs, and hyper-relational graphs. We explain the notion of feature extractor, while specifically referring to visual and semantic features. We provide a broad overview of knowledge graph embedding methods and describe several joint training objectives suitable to combine them with high dimensional visual embeddings. The main section introduces four different categories on how a KG can be combined with a DL pipeline: 1) Knowledge Graph as a Reviewer; 2) Knowledge Graph as a Trainee; 3) Knowledge Graph as a Trainer; and 4) Knowledge Graph as a Peer. To help researchers find meaningful evaluation benchmarks, we provide an overview of generic KGs and a set of image processing datasets and benchmarks that include various types of auxiliary knowledge. Last, we summarize related surveys and give an outlook about challenges and open issues for future research.

show abstract

“…Wikipeople dataset introduced by [5] is based on the publicly available Wikidata and hence can be used without violating the privacy of the people in the resulting graphs. Manual evaluation of the correctness of these models is not possible at scale.…”

Section: Existing Datasetsmentioning

confidence: 99%

Link Prediction using Graph Neural Networks for Master Data Management

Ganesan,

Parkala,

Singh

et al. 2020

Preprint

0

View full text Add to dashboard Cite

Learning graph representations of n-ary relational data has a number of real world applications like anti-money laundering, fraud detection, risk assessment etc. Graph Neural Networks have been shown to be effective in predicting links with few or no node features. While a number of datasets exist for link prediction, their features are considerably different from real world applications. Temporal information on entities and relations are often unavailable. We introduce a new dataset with 10 subgraphs, 20912 nodes, 67564 links, 70 attributes and 9 relation types. We also present novel improvements to graph models to adapt them for industry scale applications.

show abstract

Link Prediction on N-ary Relational Data

Cited by 86 publications

References 28 publications

A survey on visual transfer learning using knowledge graphs

A survey on visual transfer learning using knowledge graphs

A Survey on Visual Transfer Learning using Knowledge Graphs

Link Prediction using Graph Neural Networks for Master Data Management

Contact Info

Product

Resources

About