Skip to main content

Machine learning with graphs

Machine learning with graphs, Shobeir Fakhraei



 







Data that are best represented as a graph such as social, biological, communication, or transportation networks, and energy grids are ubiquitous in our world today. As more of such structured and semi-structured data is becoming available, the machine learning methods that can leverage the signal in these data are becoming more valuable, and the importance of being able to effectively mine and learn from such data is growing.

These graphs are typically multi-relational, dynamic, and large-scale. Understanding the different techniques applicable to graph data, dealing with their heterogeneity and applications of methods for information integration and alignment, handling dynamic and changing graphs, and addressing each of these issues at scale are some of the challenges in developing machine learning methods for graph data that appear in a variety of applications.

In this special issue, we aim to publish articles that help us better understand the principles, limitations, and applications of current graph-based machine learning methods, and to inspire research on new algorithms, techniques, and domain analysis for machine learning with graphs.

Lead guest editor
Shobeir Fakhraei, Information Science Institute, Univ. of Southern California
Guest editors
Austin Benson, Computer Science Department, Cornell University
Ciro Cattuto, ISI Foundation
Danai Koutra, Computer Science & Engineering, University of Michigan
Vagelis Papalexakis, Computer Science & Engineering, UC Riverside
Jiliang Tang, Computer Science & Engineering Dept., Michigan State University


  1. Large-scale network mining and analysis is key to revealing the underlying dynamics of networks, not easily observable before. Lately, there is a fast-growing interest in learning low-dimensional continuous re...

    Authors: Farzaneh Heidari and Manos Papagelis
    Citation: Applied Network Science 2020 5:18
    Content type: Research Published on:

  3. Learning low-dimensional representations of graphs has facilitated the use of traditional machine learning techniques to solving classic network analysis tasks such as link prediction, node classification, com...

    Authors: Seyedsaeed Hajiseyedjavadi, Yu-Ru Lin and Konstantinos Pelechrinis
    Citation: Applied Network Science 2019 4:125
    Content type: Research Published on:

  5. One can point to a variety of historical milestones for gender equality in STEM (science, technology, engineering, and mathematics), however, practical effects are incremental and ongoing. It is important to q...

    Authors: Gecia Bravo-Hermsdorff, Valkyrie Felso, Emily Ray, Lee M. Gunderson, Mary E. Helander, Joana Maria and Yael Niv
    Citation: Applied Network Science 2019 4:112
    Content type: Review Published on:

  6. Many complex processes can be viewed as dynamical systems on networks. However, in real cases, only the performances of the system are known, the network structure and the dynamical rules are not observed. The...

    Authors: Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyi Tao, Ruyue Xin and Jiang Zhang
    Citation: Applied Network Science 2019 4:110
    Content type: Research Published on:

  7. Important data mining problems such as nearest-neighbor search and clustering admit theoretical guarantees when restricted to objects embedded in a metric space. Graphs are ubiquitous, and clustering and class...

    Authors: José Bento and Stratis Ioannidis
    Citation: Applied Network Science 2019 4:107
    Content type: Research Published on:

  9. The goal of this study is to demonstrate how network science and graph theory tools and concepts can be effectively used for exploring and comparing semantic spaces of word embeddings and lexical databases. Sp...

    Authors: Alexander Veremyev, Alexander Semenov, Eduardo L. Pasiliao and Vladimir Boginski
    Citation: Applied Network Science 2019 4:104
    Content type: Research Published on:

  11. The success of graph embeddings or nodrepresentation learning in a variety of downstream tasks, such as node classification, link prediction, and recommendation systems, has led to their popularity in recent y...

    Authors: Saba A. Al-Sayouri, Danai Koutra, Evangelos E. Papalexakis and Sarah S. Lam
    Citation: Applied Network Science 2019 4:88
    Content type: Research Published on:

  12. A main challenge in mining network-based data is finding effective ways to represent or encode graph structures so that it can be efficiently exploited by machine learning algorithms. Several methods have focu...

    Authors: Leonardo Gutiérrez-Gómez and Jean-Charles Delvenne
    Citation: Applied Network Science 2019 4:82
    Content type: Research Published on:

  13. Similarity measures are used extensively in machine learning and data science algorithms. The newly proposed graph Relative Hausdorff (RH) distance is a lightweight yet nuanced similarity measure for quantifyi...

    Authors: Sinan G. Aksoy, Kathleen E. Nowak, Emilie Purvine and Stephen J. Young
    Citation: Applied Network Science 2019 4:80
    Content type: Research Published on:

  15. Information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, and biological networks. The primary challenge in...

    Authors: Mehmet E. Aktas, Esra Akbas and Ahmed El Fatmaoui
    Citation: Applied Network Science 2019 4:61
    Content type: Review Published on:

  16. PageRank for Semi-Supervised Learning has shown to leverage data structures and limited tagged examples to yield meaningful classification. Despite successes, classification performance can still be improved, ...

    Authors: Esteban Bautista, Patrice Abry and Paulo Gonçalves
    Citation: Applied Network Science 2019 4:57
    Content type: Research Published on: