An official website of the United States government
Data from many real-world applications can be naturally represented by multi-view networks where the different views encode different types of relationships (e.g., friendship, shared interests in music, etc.) between real-world individuals or entities. There is an urgent need for methods to obtain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi-view learning focuses on data that lack a network structure, and most of the work on network embeddings has focused primarily on single-view networks. Against this background, we consider the multi-view network representation learning problem, i.e., the problem of constructing low-dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the information from the individual network views, while accounting for connectivity across (and hence complementarity of and correlations between) different views. The results of our experiments on two real-world multi-view data sets show that the embeddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.
more »
« less
Search for core collapse supernovae signals in LIGO’s third observation run using a network of gravitational wave detectors integrated with a multiclass convolutional neural network
- Award ID(s):
- 2334389
- PAR ID:
- 10542460
- Publisher / Repository:
- American Physical Society
- Date Published:
- Journal Name:
- Physical Review D
- Volume:
- 110
- Issue:
- 6
- ISSN:
- 2470-0010; PRVDAQ
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Data from many real-world applications can be nat- urally represented by multi-view networks where the different views encode different types of rela- tionships (e.g., friendship, shared interests in mu- sic, etc.) between real-world individuals or enti- ties. There is an urgent need for methods to ob- tain low-dimensional, information preserving and typically nonlinear embeddings of such multi-view networks. However, most of the work on multi- view learning focuses on data that lack a net- work structure, and most of the work on net- work embeddings has focused primarily on single- view networks. Against this background, we con- sider the multi-view network representation learn- ing problem, i.e., the problem of constructing low- dimensional information preserving embeddings of multi-view networks. Specifically, we investigate a novel Generative Adversarial Network (GAN) framework for Multi-View Network Embedding, namely MEGAN, aimed at preserving the informa- tion from the individual network views, while ac- counting for connectivity across (and hence com- plementarity of and correlations between) differ- ent views. The results of our experiments on two real-world multi-view data sets show that the em- beddings obtained using MEGAN outperform the state-of-the-art methods on node classification, link prediction and visualization tasks.more » « less
-
The Graduate Research Identity Development program (GRID) is an initiative in the College of Engineering at North Carolina A&T State University, sponsored by the National Science Foundation since 2019. The program offers seminar-type lectures supplemented with activities designed to help graduate students develop critical skills for research-based careers. The program is focused on graduate engineering students but is open to graduate students from all programs. Students also choose mentors from within and outside the university with the goal of increasing their sense of belonging to the field and their identities as research engineers. As part of this program, a pilot study is in progress, aimed at performing a full-scale network analysis of student interactions. A web-based survey was administered to collect information about students in and outside the College of Engineering who participate in the GRID program sessions. The survey was designed to collect information on the relationship networks (or lack thereof) that students are involved in as they matriculate through their graduate program. It assesses things such as how and where the students interact with one another, members of faculty and staff, and with contacts from intramural and extramural organizations. Several items are also used to assess students’ perceptions of themselves as research engineers. In this paper, we focus on the interactions of students in the classroom. More specifically, we form networks based on the student answers about the classes they have taken in different departments. We then analyze the resultant networks and contrast certain graph theoretic properties to students’ scores on the research engineer identity items. Do students that are in the periphery, or students that have more connections attain higher research engineer identity scores? Do students that form complete subnetworks (cliques) or core-periphery structures (induced stars) have higher scores than others? This paper presents the findings from this pilot study from the network analysis on this cohort of students. In summary, we find that students with high eigenvector centrality scores and those who form larger cliques possess significantly higher research engineer identity scores.more » « less
-
null (Ed.)
