Abstract
This formal correction notice addresses clerical errors in the 2019 research paper "Learning Graph Topological Features via GAN," originally published in IEEE Access (Volume 7). The update officially incorporates three missing co-authors from Columbia University—Hal Cooper, Min-Hwan Oh, and Sailung Yeung—and acknowledges essential funding support from the IBM Watson Research Center that was inadvertently omitted in the initial publication.
Introduction
In the academic community, the integrity of the scientific record relies heavily on the accurate attribution of credit and the transparent disclosure of financial support. Proper authorship is not merely a matter of prestige; it is critical for career development, institutional records, and the accountability of research findings. This document serves as a "Comments and Corrections" notice to rectify significant omissions in the paper "Learning Graph Topological Features via GAN." By updating the author list and funding acknowledgments, this notice ensures that the collaborative efforts and resources behind the study are fully recognized.
Author and Affiliation Corrections
The original submission process for the 2019 paper inadvertently excluded three key contributors from Columbia University. These individuals played substantial roles in the research, and their inclusion provides a more complete picture of the expertise required to develop GAN-based models for graph topological features. The updated author list now formally includes:
- Hal Cooper (Columbia University)
- Min-Hwan Oh (Columbia University)
- Sailung Yeung (Columbia University)
The addition of these researchers suggests that the original work was a highly collaborative effort, likely bridging the gap between theoretical machine learning and practical graph computing systems.
Funding Acknowledgement
Beyond authorship, the original publication failed to credit the IBM Watson Research Center for its partial funding of the work. Funding acknowledgments are vital for demonstrating the impact of research grants and the involvement of industrial partners in academic advancements. This correction officially recognizes the IBM Watson Research Center's financial and institutional support, which was instrumental in the completion of the study.
Biographical Profiles of New Co-authors
The expertise of the newly added co-authors sheds light on the multi-faceted nature of the original research. Their backgrounds suggest a combination of high-performance computing, decision theory, and optimization.
Hal Cooper
Hal Cooper is a Ph.D. student at Columbia University. His research interests lie at the intersection of graph databases and high-performance computing. Specifically, he focuses on developing technologies capable of handling massively concurrent access, a requirement often found in real-world industrial graph applications. Hal Cooper, Ph.D. student at Columbia University specializing in graph databases. Corrections to "Learning Graph Topological Features via GAN", page 1
Min-Hwan Oh
Min-Hwan Oh is a Ph.D. student at Columbia University whose work centers on sequential decision-making under uncertainty. His expertise includes contextual bandits and reinforcement learning, fields that are increasingly relevant to the dynamic analysis of graph-structured data. Min-Hwan Oh, Ph.D. student at Columbia University focusing on reinforcement learning. Corrections to "Learning Graph Topological Features via GAN", page 1
Sailung Yeung
Sailung Yeung is a Master's student at Columbia University. His contributions to the research involve optimization, machine learning, and quantitative analysis. His background likely supported the algorithmic refinement and performance evaluation of the GAN models discussed in the original paper.
Conclusion
While this notice does not alter the technical findings or methodologies of the original paper—which utilized Generative Adversarial Networks (GANs) to learn topological features of graphs—it is a necessary step in maintaining the standards of academic publishing. The inclusion of Hal Cooper, Min-Hwan Oh, and Sailung Yeung, along with the acknowledgment of the IBM Watson Research Center, provides a complete and accurate account of the intellectual and financial foundations of the research.
Summary updated