Scientific Impact of Graph-Based Approaches in Deep Learning Studies -- A Bibliometric Comparison

• URL: http://arxiv.org/abs/2210.07343v1
• Date: Thu, 13 Oct 2022 20:23:43 GMT
• Title: Scientific Impact of Graph-Based Approaches in Deep Learning Studies -- A Bibliometric Comparison
• Authors: Ilker Turker, Serhat Orkun Tan
• Abstract summary: It's outlined that deep learning-based studies gained momentum after year 2013, and the rate of graph-based approaches in all deep learning studies increased linearly from 1% to 4% within the following 10 years. Despite their similar performance in recent years, graph-based studies show twice more citation performance as they get older, compared to traditional approaches.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Applying graph-based approaches in deep learning receives more attention over time. This study presents statistical analysis on the use of graph-based approaches in deep learning and examines the scientific impact of the related articles. Processing the data obtained from the Web of Science database, metrics such as the type of the articles, funding availability, indexing type, annual average number of citations and the number of access were analyzed to quantitatively reveal the effects on the scientific audience. It's outlined that deep learning-based studies gained momentum after year 2013, and the rate of graph-based approaches in all deep learning studies increased linearly from 1% to 4% within the following 10 years. Conference publications scanned in the Conference Proceeding Citation Index (CPCI) on the graph-based approaches receive significantly more citations. The citation counts of the SCI-Expanded and Emerging SCI indexed publications of the two streams are close to each other. While the citation performances of the supported and unsupported publications of the two sides were similar, pure deep learning studies received more citations on the journal publication side and graph-based approaches received more citations on the conference side. Despite their similar performance in recent years, graph-based studies show twice more citation performance as they get older, compared to traditional approaches. Annual average citation performance per article for all deep learning studies is 11.051 in 2014, while it is 22.483 for graph-based studies. Also, despite receiving 16% more access, graph-based papers get almost the same overall citation over time with the pure counterpart. This is an indication that graph-based approaches need a greater bunch of attention to follow, while pure deep learning counterpart is relatively simpler to get inside.

Related papers

• Mapping the Increasing Use of LLMs in Scientific Papers [99.67983375899719]
  We conduct the first systematic, large-scale analysis across 950,965 papers published between January 2020 and February 2024 on the arXiv, bioRxiv, and Nature portfolio journals. Our findings reveal a steady increase in LLM usage, with the largest and fastest growth observed in Computer Science papers.
  arXiv  Detail & Related papers  (2024-04-01T17:45:15Z)
• H2CGL: Modeling Dynamics of Citation Network for Impact Prediction [13.00224680454585]
  We construct hierarchical and heterogeneous graphs for target papers with an annual perspective. The graphs can record the annual dynamics of target papers' scientific context information. A novel graph neural network, Hierarchical and Heterogeneous Contrastive Graph Learning Model, is proposed.
  arXiv  Detail & Related papers  (2023-04-16T13:04:32Z)
• State of the Art and Potentialities of Graph-level Learning [54.68482109186052]
  Graph-level learning has been applied to many tasks including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs rely on hand-crafted features, such as substructures. Deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations.
  arXiv  Detail & Related papers  (2023-01-14T09:15:49Z)
• Machine Learning vs. Deep Learning in 5G Networks -- A Comparison of Scientific Impact [0.0]
  Machine learning (ML) and deep learning (DL) techniques are used in 5G networks. Our study aims to uncover the differences in scientific impact for these two techniques by the means of statistical bibliometrics. Web of Science (WoS) database host 2245 papers for ML and 1407 papers for DL-related studies.
  arXiv  Detail & Related papers  (2022-10-13T19:54:17Z)
• Citation Trajectory Prediction via Publication Influence Representation Using Temporal Knowledge Graph [52.07771598974385]
  Existing approaches mainly rely on mining temporal and graph data from academic articles. Our framework is composed of three modules: difference-preserved graph embedding, fine-grained influence representation, and learning-based trajectory calculation. Experiments are conducted on both the APS academic dataset and our contributed AIPatent dataset.
  arXiv  Detail & Related papers  (2022-10-02T07:43:26Z)
• Research Trends and Applications of Data Augmentation Algorithms [77.34726150561087]
  We identify the main areas of application of data augmentation algorithms, the types of algorithms used, significant research trends, their progression over time and research gaps in data augmentation literature. We expect readers to understand the potential of data augmentation, as well as identify future research directions and open questions within data augmentation research.
  arXiv  Detail & Related papers  (2022-07-18T11:38:32Z)
• Deep Graph Learning for Anomalous Citation Detection [55.81334139806342]
  We propose a novel deep graph learning model, namely GLAD (Graph Learning for Anomaly Detection), to identify anomalies in citation networks. Within the GLAD framework, we propose an algorithm called CPU (Citation PUrpose) to discover the purpose of citation based on citation texts.
  arXiv  Detail & Related papers  (2022-02-23T09:05:28Z)
• A Graph Convolutional Neural Network based Framework for Estimating Future Citations Count of Research Articles [0.03937354192623676]
  We propose a Graph Convolutional Network (GCN) based framework for estimating future research publication citations for both the short-term (1-year) and long-term (for 5-years and 10-years) duration. We have tested our proposed approach over the AMiner dataset, specifically on research articles from the computer science domain, consisting of more than 0.8 million articles.
  arXiv  Detail & Related papers  (2021-04-11T07:20:53Z)
• Enhancing Scientific Papers Summarization with Citation Graph [78.65955304229863]
  We redefine the task of scientific papers summarization by utilizing their citation graph. We construct a novel scientific papers summarization dataset Semantic Scholar Network (SSN) which contains 141K research papers in different domains. Our model can achieve competitive performance when compared with the pretrained models.
  arXiv  Detail & Related papers  (2021-04-07T11:13:35Z)
• Structured Citation Trend Prediction Using Graph Neural Networks [6.325999141414098]
  We present a GNN-based architecture that predicts the top set of papers at the time of publication. For experiments, we curate a set of academic citation graphs for a variety of conferences and show that the proposed model outperforms other classic machine learning models in terms of the F1-score.
  arXiv  Detail & Related papers  (2021-04-06T14:58:29Z)
• The Demise of Single-Authored Publications in Computer Science: A Citation Network Analysis [0.0]
  I analyze the DBLP database to study role of single author publications in the computer science literature between 1940 and 2019. I examine the demographics and reception by computing the population fraction, citation statistics, and scores of single author publications over the years.
  arXiv  Detail & Related papers  (2020-01-02T07:47:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.