scholarly journals Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction

2020 ◽  
Author(s):  
Tara Safavi ◽  
Danai Koutra ◽  
Edgar Meij
Keyword(s):  
Link Prediction ◽  
Knowledge Graph ◽  
Graph Embeddings

scholarly journals Learning Translation-Based Knowledge Graph Embeddings by N-Pair Translation Loss

2020 ◽  
Vol 10 (11) ◽  
pp. 3964
Author(s):  
Hyun-Je Song ◽  
A-Yeong Kim ◽  
Seong-Bae Park
Keyword(s):  
Link Prediction ◽  
Early Stage ◽  
Score Function ◽  
Knowledge Graph ◽  
Graph Embeddings ◽  
Local Optima ◽  
Slow Convergence ◽  
Translation Operators ◽  
Vector Representations ◽  
Ranking Loss

Translation-based knowledge graph embeddings learn vector representations of entities and relations by treating relations as translation operators over the entities in an embedding space. Since the translation is represented through a score function, translation-based embeddings are trained in general by minimizing a margin-based ranking loss, which assigns a low score to positive triples and a high score to negative triples. However, this type of embedding suffers from slow convergence and poor local optima because the loss adopts only one pair of a positive and a negative triple at a single update of learning parameters. Therefore, this paper proposes the N-pair translation loss that considers multiple negative triples at one update. The N-pair translation loss employs multiple negative triples as well as one positive triple and allows the positive triple to be compared against the multiple negative triples at each parameter update. As a result, it becomes possible to obtain better vector representations rapidly. The experimental results on link prediction prove that the proposed loss helps to quickly converge toward good optima at the early stage of training.

scholarly journals Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction – two sides of the same coin?

Semantic Web ◽  
2022 ◽  
pp. 1-24
Author(s):  
Jan Portisch ◽  
Nicolas Heist ◽  
Heiko Paulheim
Keyword(s):  
Data Mining ◽  
Link Prediction ◽  
Graph Embedding ◽  
Knowledge Graph ◽  
Graph Embeddings ◽  
Similarity Functions ◽  
Evaluation Methodologies ◽  
Series Of Experiments ◽  
Two Sides ◽  
Lower Dimensional

Knowledge Graph Embeddings, i.e., projections of entities and relations to lower dimensional spaces, have been proposed for two purposes: (1) providing an encoding for data mining tasks, and (2) predicting links in a knowledge graph. Both lines of research have been pursued rather in isolation from each other so far, each with their own benchmarks and evaluation methodologies. In this paper, we argue that both tasks are actually related, and we show that the first family of approaches can also be used for the second task and vice versa. In two series of experiments, we provide a comparison of both families of approaches on both tasks, which, to the best of our knowledge, has not been done so far. Furthermore, we discuss the differences in the similarity functions evoked by the different embedding approaches.

scholarly journals Representing a Heterogeneous Pharmaceutical Knowledge-Graph with Textual Information

2021 ◽  
Vol 6 ◽  
Author(s):  
Masaki Asada ◽  
Nallappan Gunasekaran ◽  
Makoto Miwa ◽  
Yutaka Sasaki
Keyword(s):  
Drug Discovery ◽  
Link Prediction ◽  
Knowledge Graph ◽  
Graph Embeddings ◽  
Textual Information ◽  
Prediction Task

We deal with a heterogeneous pharmaceutical knowledge-graph containing textual information built from several databases. The knowledge graph is a heterogeneous graph that includes a wide variety of concepts and attributes, some of which are provided in the form of textual pieces of information which have not been targeted in the conventional graph completion tasks. To investigate the utility of textual information for knowledge graph completion, we generate embeddings from textual descriptions given to heterogeneous items, such as drugs and proteins, while learning knowledge graph embeddings. We evaluate the obtained graph embeddings on the link prediction task for knowledge graph completion, which can be used for drug discovery and repurposing. We also compare the results with existing methods and discuss the utility of the textual information.

scholarly journals Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction

2020 ◽  
Author(s):  
Samuel Broscheit ◽  
Kiril Gashteovski ◽  
Yanjie Wang ◽  
Rainer Gemulla
Keyword(s):  
Link Prediction ◽  
Knowledge Graph ◽  
Graph Embeddings

scholarly journals Shall I Work with Them? A Knowledge Graph-Based Approach for Predicting Future Research Collaborations

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 664
Author(s):  
Nikos Kanakaris ◽  
Nikolaos Giarelis ◽  
Ilias Siachos ◽  
Nikos Karacapilidis
Keyword(s):  
Language Processing ◽  
Scientific Knowledge ◽  
Link Prediction ◽  
Performance Metrics ◽  
Future Research ◽  
Knowledge Graph ◽  
Prediction Problem ◽  
Textual Information ◽  
Research Collaborations ◽  
Processing Techniques

We consider the prediction of future research collaborations as a link prediction problem applied on a scientific knowledge graph. To the best of our knowledge, this is the first work on the prediction of future research collaborations that combines structural and textual information of a scientific knowledge graph through a purposeful integration of graph algorithms and natural language processing techniques. Our work: (i) investigates whether the integration of unstructured textual data into a single knowledge graph affects the performance of a link prediction model, (ii) studies the effect of previously proposed graph kernels based approaches on the performance of an ML model, as far as the link prediction problem is concerned, and (iii) proposes a three-phase pipeline that enables the exploitation of structural and textual information, as well as of pre-trained word embeddings. We benchmark the proposed approach against classical link prediction algorithms using accuracy, recall, and precision as our performance metrics. Finally, we empirically test our approach through various feature combinations with respect to the link prediction problem. Our experimentations with the new COVID-19 Open Research Dataset demonstrate a significant improvement of the abovementioned performance metrics in the prediction of future research collaborations.

Sign in / Sign up

Export Citation Format

Share Document