scholarly journals A survey on visual transfer learning using knowledge graphs

Semantic Web ◽  
2022 ◽  
pp. 1-34
Author(s):  
Sebastian Monka ◽  
Lavdim Halilaj ◽  
Achim Rettinger
Keyword(s):  
Transfer Learning ◽  
Real World ◽  
Image Data ◽  
Graph Embedding ◽  
Future Research ◽  
Knowledge Graph ◽  
Semantic Features ◽  
Learning Approaches ◽  
Knowledge Graphs ◽  
Relational Graphs

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.

scholarly journals TransET: Knowledge Graph Embedding with Entity Types

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1407
Author(s):  
Peng Wang ◽  
Jing Zhou ◽  
Yuzhang Liu ◽  
Xingchen Zhou
Keyword(s):  
Link Prediction ◽  
State Of The Art ◽  
Score Function ◽  
Graph Embedding ◽  
Vector Spaces ◽  
Knowledge Graph ◽  
Semantic Features ◽  
Knowledge Graphs ◽  
Real World Datasets ◽  
Low Dimensional

Knowledge graph embedding aims to embed entities and relations into low-dimensional vector spaces. Most existing methods only focus on triple facts in knowledge graphs. In addition, models based on translation or distance measurement cannot fully represent complex relations. As well-constructed prior knowledge, entity types can be employed to learn the representations of entities and relations. In this paper, we propose a novel knowledge graph embedding model named TransET, which takes advantage of entity types to learn more semantic features. More specifically, circle convolution based on the embeddings of entity and entity types is utilized to map head entity and tail entity to type-specific representations, then translation-based score function is used to learn the presentation triples. We evaluated our model on real-world datasets with two benchmark tasks of link prediction and triple classification. Experimental results demonstrate that it outperforms state-of-the-art models in most cases.

scholarly journals Entity Alignment between Knowledge Graphs Using Attribute Embeddings

2019 ◽  
Vol 33 ◽  
pp. 297-304 ◽  
Author(s):  
Bayu Distiawan Trisedya ◽  
Jianzhong Qi ◽  
Rui Zhang
Keyword(s):  
Real World ◽  
Graph Embedding ◽  
Knowledge Bases ◽  
Knowledge Graph ◽  
World Knowledge ◽  
Large Numbers ◽  
Proposed Model ◽  
Alignment Task ◽  
Transitivity Rule ◽  
Knowledge Graphs

The task of entity alignment between knowledge graphs aims to find entities in two knowledge graphs that represent the same real-world entity. Recently, embedding-based models are proposed for this task. Such models are built on top of a knowledge graph embedding model that learns entity embeddings to capture the semantic similarity between entities in the same knowledge graph. We propose to learn embeddings that can capture the similarity between entities in different knowledge graphs. Our proposed model helps align entities from different knowledge graphs, and hence enables the integration of multiple knowledge graphs. Our model exploits large numbers of attribute triples existing in the knowledge graphs and generates attribute character embeddings. The attribute character embedding shifts the entity embeddings from two knowledge graphs into the same space by computing the similarity between entities based on their attributes. We use a transitivity rule to further enrich the number of attributes of an entity to enhance the attribute character embedding. Experiments using real-world knowledge bases show that our proposed model achieves consistent improvements over the baseline models by over 50% in terms of hits@1 on the entity alignment task.

scholarly journals Logic Attention Based Neighborhood Aggregation for Inductive Knowledge Graph Embedding

2019 ◽  
Vol 33 ◽  
pp. 7152-7159 ◽  
Author(s):  
Peifeng Wang ◽  
Jialong Han ◽  
Chenliang Li ◽  
Rong Pan
Keyword(s):  
Real World ◽  
Graph Embedding ◽  
Daily Basis ◽  
Knowledge Graph ◽  
World Knowledge ◽  
Attention Network ◽  
Knowledge Graphs ◽  
Low Dimensional

Knowledge graph embedding aims at modeling entities and relations with low-dimensional vectors. Most previous methods require that all entities should be seen during training, which is unpractical for real-world knowledge graphs with new entities emerging on a daily basis. Recent efforts on this issue suggest training a neighborhood aggregator in conjunction with the conventional entity and relation embeddings, which may help embed new entities inductively via their existing neighbors. However, their neighborhood aggregators neglect the unordered and unequal natures of an entity’s neighbors. To this end, we summarize the desired properties that may lead to effective neighborhood aggregators. We also introduce a novel aggregator, namely, Logic Attention Network (LAN), which addresses the properties by aggregating neighbors with both rules- and network-based attention weights. By comparing with conventional aggregators on two knowledge graph completion tasks, we experimentally validate LAN’s superiority in terms of the desired properties.

scholarly journals Bootstrapping Entity Alignment with Knowledge Graph Embedding

2018 ◽  
Author(s):  
Zequn Sun ◽  
Wei Hu ◽  
Qingheng Zhang ◽  
Yuzhong Qu
Keyword(s):  
Performance Improvement ◽  
Real World ◽  
State Of The Art ◽  
Graph Embedding ◽  
Training Data ◽  
Knowledge Graph ◽  
Error Accumulation ◽  
Knowledge Graphs ◽  
Real World Datasets ◽  
Low Dimensional

Embedding-based entity alignment represents different knowledge graphs (KGs) as low-dimensional embeddings and finds entity alignment by measuring the similarities between entity embeddings. Existing approaches have achieved promising results, however, they are still challenged by the lack of enough prior alignment as labeled training data. In this paper, we propose a bootstrapping approach to embedding-based entity alignment. It iteratively labels likely entity alignment as training data for learning alignment-oriented KG embeddings. Furthermore, it employs an alignment editing method to reduce error accumulation during iterations. Our experiments on real-world datasets showed that the proposed approach significantly outperformed the state-of-the-art embedding-based ones for entity alignment. The proposed alignment-oriented KG embedding, bootstrapping process and alignment editing method all contributed to the performance improvement.

scholarly journals Link Prediction between Group Entities in Knowledge Graphs (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13925-13926
Author(s):  
Jialin Su ◽  
Yuanzhuo Wang ◽  
Xiaolong Jin ◽  
Yantao Jia ◽  
Xueqi Cheng
Keyword(s):  
Real World ◽  
Heterogeneous Network ◽  
Link Prediction ◽  
Graph Embedding ◽  
Knowledge Graph ◽  
Low Dimension ◽  
Individual Entity ◽  
Knowledge Graphs ◽  
Dimension Space

Link prediction in knowledge graphs (KGs) aims at predicting potential links between entities in KGs. Existing knowledge graph embedding (KGE) based methods represent individual entities and links in KGs as vectors in low-dimension space. However, these methods focus mainly on the link prediction of individual entities, yet neglect that between group entities, which exist widely in real-world KGs. In this paper, we propose a KGE based method, called GTransA, for link prediction between group entities in a heterogeneous network by integrating individual entity links into group entity links during prediction. Experiments show that GTransA decreases mean rank by 5.4%, compared to TransA.

scholarly journals Multi-view Knowledge Graph Embedding for Entity Alignment

2019 ◽  
Author(s):  
Qingheng Zhang ◽  
Zequn Sun ◽  
Wei Hu ◽  
Muhao Chen ◽  
Lingbing Guo ◽  
...  
Keyword(s):  
Performance Improvement ◽  
Real World ◽  
State Of The Art ◽  
Graph Embedding ◽  
Knowledge Graph ◽  
Multiple Views ◽  
Combination Strategies ◽  
Knowledge Graphs ◽  
Real World Datasets ◽  
Inference Methods

We study the problem of embedding-based entity alignment between knowledge graphs (KGs). Previous works mainly focus on the relational structure of entities. Some further incorporate another type of features, such as attributes, for refinement. However, a vast of entity features are still unexplored or not equally treated together, which impairs the accuracy and robustness of embedding-based entity alignment. In this paper, we propose a novel framework that unifies multiple views of entities to learn embeddings for entity alignment. Specifically, we embed entities based on the views of entity names, relations and attributes, with several combination strategies. Furthermore, we design some cross-KG inference methods to enhance the alignment between two KGs. Our experiments on real-world datasets show that the proposed framework significantly outperforms the state-of-the-art embedding-based entity alignment methods. The selected views, cross-KG inference and combination strategies all contribute to the performance improvement.

scholarly journals Virtual Knowledge Graphs: An Overview of Systems and Use Cases

2019 ◽  
Vol 1 (3) ◽  
pp. 201-223 ◽  
Author(s):  
Guohui Xiao ◽  
Linfang Ding ◽  
Benjamin Cogrel ◽  
Diego Calvanese
Keyword(s):  
Data Integration ◽  
Domain Knowledge ◽  
Data Access ◽  
Use Cases ◽  
Future Research ◽  
Knowledge Graph ◽  
Research Directions ◽  
Wide Range ◽  
Future Research Directions ◽  
Knowledge Graphs

In this paper, we present the virtual knowledge graph (VKG) paradigm for data integration and access, also known in the literature as Ontology-based Data Access. Instead of structuring the integration layer as a collection of relational tables, the VKG paradigm replaces the rigid structure of tables with the flexibility of graphs that are kept virtual and embed domain knowledge. We explain the main notions of this paradigm, its tooling ecosystem and significant use cases in a wide range of applications. Finally, we discuss future research directions.

Conclusion

2017 ◽  
pp. 217-229 ◽  
Author(s):  
Pradeep Kumar
Keyword(s):  
Machine Learning ◽  
Object Recognition ◽  
Pattern Matching ◽  
Real World ◽  
Systematic Position ◽  
Future Research ◽  
Learning Approaches ◽  
Research And Practice ◽  
Supervised And Unsupervised Learning ◽  
Classification Prediction

This chapter summarize and concludes the issues and challenges elaborated in different chapters using machine learning approaches presented by various authors. It identifies the importance of supervised and unsupervised learning algorithms establishing classification, prediction, clustering, security policies along with object recognition and pattern matching structures. A systematic position for future research and practice is also described in detail. This book presents the capabilities of machine learning methods and ideas on how these methods could be used to solve real-world problems related to health, social and engineering applications.

scholarly journals Learning Hierarchy-Aware Knowledge Graph Embeddings for Link Prediction

2020 ◽  
Vol 34 (03) ◽  
pp. 3065-3072 ◽  
Author(s):  
Zhanqiu Zhang ◽  
Jianyu Cai ◽  
Yongdong Zhang ◽  
Jie Wang
Keyword(s):  
Coordinate System ◽  
Link Prediction ◽  
Graph Embedding ◽  
Knowledge Graph ◽  
Polar Coordinate System ◽  
Radial Coordinate ◽  
Polar Coordinate ◽  
Benchmark Datasets ◽  
Knowledge Graphs ◽  
Semantic Hierarchies

Knowledge graph embedding, which aims to represent entities and relations as low dimensional vectors (or matrices, tensors, etc.), has been shown to be a powerful technique for predicting missing links in knowledge graphs. Existing knowledge graph embedding models mainly focus on modeling relation patterns such as symmetry/antisymmetry, inversion, and composition. However, many existing approaches fail to model semantic hierarchies, which are common in real-world applications. To address this challenge, we propose a novel knowledge graph embedding model—namely, Hierarchy-Aware Knowledge Graph Embedding (HAKE)—which maps entities into the polar coordinate system. HAKE is inspired by the fact that concentric circles in the polar coordinate system can naturally reflect the hierarchy. Specifically, the radial coordinate aims to model entities at different levels of the hierarchy, and entities with smaller radii are expected to be at higher levels; the angular coordinate aims to distinguish entities at the same level of the hierarchy, and these entities are expected to have roughly the same radii but different angles. Experiments demonstrate that HAKE can effectively model the semantic hierarchies in knowledge graphs, and significantly outperforms existing state-of-the-art methods on benchmark datasets for the link prediction task.

scholarly journals Biological applications of knowledge graph embedding models

2020 ◽  
Author(s):  
Sameh K Mohamed ◽  
Aayah Nounu ◽  
Vít Nováček
Keyword(s):  
Predictive Accuracy ◽  
Biological Systems ◽  
Graph Embedding ◽  
Low Rank ◽  
Superior Performance ◽  
Knowledge Graph ◽  
Biological Knowledge ◽  
Knowledge Graphs ◽  
Vector Representations ◽  
Biological Entities

Abstract Complex biological systems are traditionally modelled as graphs of interconnected biological entities. These graphs, i.e. biological knowledge graphs, are then processed using graph exploratory approaches to perform different types of analytical and predictive tasks. Despite the high predictive accuracy of these approaches, they have limited scalability due to their dependency on time-consuming path exploratory procedures. In recent years, owing to the rapid advances of computational technologies, new approaches for modelling graphs and mining them with high accuracy and scalability have emerged. These approaches, i.e. knowledge graph embedding (KGE) models, operate by learning low-rank vector representations of graph nodes and edges that preserve the graph’s inherent structure. These approaches were used to analyse knowledge graphs from different domains where they showed superior performance and accuracy compared to previous graph exploratory approaches. In this work, we study this class of models in the context of biological knowledge graphs and their different applications. We then show how KGE models can be a natural fit for representing complex biological knowledge modelled as graphs. We also discuss their predictive and analytical capabilities in different biology applications. In this regard, we present two example case studies that demonstrate the capabilities of KGE models: prediction of drug–target interactions and polypharmacy side effects. Finally, we analyse different practical considerations for KGEs, and we discuss possible opportunities and challenges related to adopting them for modelling biological systems.

Sign in / Sign up

Export Citation Format

Share Document