Reconstruction of missing data in transferred generative adversarial networks with small sample data

Jing He; Hongrun Chen; Zhenwen Sheng

doi:10.1371/journal.pone.0322323

Peer Review History

Original SubmissionNovember 13, 2024
13 Nov 2024 Author Response https://doi.org/10.1371/journal.pone.0322323.r001
3 Jan 2025 Decision Letter - Zeeshan Ahmad, Editor PONE-D-24-51993Reconstruction of Missing Data in Transferred Generative Adversarial Networks with Small Sample DataPLOS ONE Dear Dr. Chen, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Feb 17 2025 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org . When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols . Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols . We look forward to receiving your revised manuscript. Kind regards, Zeeshan Ahmad Academic Editor PLOS ONE Journal requirements: When submitting your revision, we need you to address these additional requirements. 1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. We note that you have indicated that there are restrictions to data sharing for this study. PLOS only allows data to be available upon request if there are legal or ethical restrictions on sharing data publicly. For more information on unacceptable data access restrictions, please see http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Before we proceed with your manuscript, please address the following prompts: a) If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially identifying or sensitive patient information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., a Research Ethics Committee or Institutional Review Board, etc.). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. b) If there are no restrictions, please upload the minimal anonymized data set necessary to replicate your study findings to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. You also have the option of uploading the data as Supporting Information files, but we would recommend depositing data directly to a data repository if possible. We will update your Data Availability statement on your behalf to reflect the information you provide. 4. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: No Reviewer #2: No ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: No ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: Under special working conditions, data collection systems of heavy-duty trains may be faced with a small sample size and missing data when executing measurement, operation, or maintenance tasks. The authors set up a frame of migration learning generative adversarial network for small data samples, in which a new variational autoencoder semantic fusion generative adversarial network (VAE-FGAN) is developed to reconstruct missing data. The topic is interesting. Some comments are given as follows: 1. The motivation for using GRU and VAE needs to be provided. There are various methods available for use. 2. The introduction needs to be more detailed. The author should summarize the existing work and provide specific advantages and disadvantages. 3. The description of Figure 1 needs to be more detailed, highlighting the main contributions. 4. How were the results of Figure 2 obtained? 5. The experimental results are not sufficient. More comparative methods need to be included. Reviewer #2: This paper tackles the important challenge of reconstructing missing data in small sample scenarios, a common issue in data collection systems for heavy-duty trains operating under special working conditions. The authors propose an innovative migration learning framework for generative adversarial networks (GANs) specifically designed to handle small data samples. The introduction of a novel variational autoencoder semantic fusion GAN (VAE-FGAN) is a significant contribution, showing promise in effectively reconstructing missing data. However, while the paper demonstrates technical merit, there are areas that require further attention and refinement. Below are my detailed comments and suggestions: 1. To enhance the paper’s formatting consistency and professionalism, the authors should ensure that all instances of “et al.” are italicized throughout the manuscript. Furthermore, the Introduction section would benefit from a brief overview of the subsequent sections. Including a sentence such as, “The remainder of this paper is organized as follows. Section 2 introduces… Section 3 discusses…” will provide the reader with a clear roadmap and improve the overall readability of the paper. 2. The manuscript lacks a dedicated discussion on related work, which is crucial for contextualizing the contribution within the broader field. It is strongly recommended to add a new section titled “Related Work” immediately following the Introduction. This section should include an overview of the basic theory of GANs and their various applications. Key papers that should be discussed include: “COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles” and “Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework”. These papers exemplify GAN applications in other fields and can serve as a comparative basis to highlight the novelty of the authors’ approach. Additionally, a review of existing work on GANs applied to missing data reconstruction is necessary to provide a comprehensive background and demonstrate how the proposed method advances the state of the art. 3. The title of Section 2.1 is overly lengthy and could be simplified for clarity and conciseness. A succinct title would not only improve readability but also align better with standard academic writing practices. 4. Fig. 4 lacks clarity regarding the model’s inputs and outputs, which are critical for understanding the workflow. It is recommended that the authors refine the figure by explicitly labeling these elements or adding a brief explanatory note. This improvement will significantly enhance the figure’s utility for readers. 5. There are typographical errors in the manuscript that need to be corrected. For example, “RuLU” should be replaced with the correct term “ReLU.” Additionally, Fig. 2 should be carefully reviewed for similar errors or inconsistencies to ensure the accuracy and professionalism of the presentation. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy . Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/ . PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org . Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0322323.r002
Revision 1
12 Mar 2025 Author Response Reviewer 1 1. The motivation for using GRU and VAE needs to be provided. There are various methods available for use. Response: Thanks for your suggestions and comments. We have incorporated the motivation of using VAE and GRU in Sections 3.2 and 3.3. VAE and GAN are two classic generative models. GAN generates good-quality data, but it is challenging to reach the Nash equilibrium during adversarial training, and it will collapse during the process, leading to the generator “cheating” the generator. Moreover, the generated data is very unreasonable. The variance measures the loss function of VAE training, which generates data that does not preserve the data features. Moreover, the latent vectors it learns during decoding can be used to generate the original data. As a result, we designed a highly stable VAE-GAN model capable of learning features to leverage the benefits of the two major generative models. Like the traditional VAE, this model learns the feature distribution of the input data through encoding and reconstruction. During the training process, the encoder E extracts and compresses the sample features in the complete dataset and encodes them into the latent space z through a linear network, where z is the important data features information being latently captured. VAE-GAN dramatically improves training stability and the quality of generated data compared to the original GAN. Therefore, we incorporated the GRU module to encoder E based on the VAE-GAN model, improving encoder E’s ability to acquire the data’s deep semantics and the quality of the generated data. 2. The Introduction needs to be more detailed. The author should summarize the existing work and provide specific advantages and disadvantages. Response: Many thanks for your suggestions and comments. We have modified the Introduction section: First, traditional missing data reconstruction methods, such as EM and KNN, fall short in describing the correlation between complex data features and different devices by reconstructing the missing data with purely mathematical models. Second, the more popular GAN models can solve the data missing problem effectively. However, due to the particularity of our dataset, it is challenging to train these GAN models with discrete data. Thus, there is no guarantee that these models can generate samples that match the original data distribution when starting from random background noise, which can lead to the vanishing of gradients and hinder reaching Nash equilibrium. While some variants of GAN models have been developed and show improved accuracy with increasing layers, they also place higher demands on the dataset and require a larger volume of training data. As a result, their effectiveness is limited when applied to small sample datasets. Considering the potential of transfer learning in small sample scenarios, we are inspired to create a data reconstruction architecture that leverages transfer learning techniques. 3. The description of Figure 1 needs to be more detailed, highlighting the main contributions. Response: Many thanks for your suggestion. In Section 3.1, we have described Figure 1 in more detail to highlight our innovation. Moreover, in the first paragraph of part 2, we have added a brief overview of the subsequent sections to provide a roadmap for the reader. 4. How were the results of Figure 2 obtained? Response: Figure 2 depicts the network structure of encoder E, generator G, and discriminator D in the VAE-FGAN network, which is the third part of Figure 1. This figure visualizes the network design. We have also modified this part in Section 3.1. 5. The experimental results are not sufficient. More comparative methods need to be included. Response: We have incorporated relevant comparative experiments in Table 4 to compare our proposed model with the traditional and some methods in the literature. Reviewer 2 1. To enhance the paper’s formatting consistency and professionalism, the authors should ensure that all instances of “et al.” are italicized throughout the manuscript. Furthermore, the Introduction section would benefit from a brief overview of the subsequent sections. Including a sentence such as, “The remainder of this paper is organized as follows. Section 2 introduces… Section 3 discusses…” will provide the reader with a clear roadmap and improve the overall readability of the paper. Response: Many thanks for your suggestions. We have reformatted the entire paper to make it more professional and improved its readability by including its roadmap at the end of the first section and the beginning of the third section. 2. The manuscript lacks a dedicated discussion on related work, which is crucial for contextualizing the contribution within the broader field. It is strongly recommended that a new section titled “Related Work” be added immediately following the introduction. This section should include an overview of the basic theory of GANs and their various applications. Key papers that should be discussed include: “COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles” and “Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework”. These papers exemplify GAN applications in other fields and can serve as a comparative basis to highlight the novelty of the authors’ approach. Additionally, a review of existing work on GANs applied to missing data reconstruction is necessary to provide a comprehensive background and demonstrate how the proposed method advances the state of the art. Response: A section devoted to related work has been incorporated into the revised version. 3. The title of Section 2.1 is overly lengthy and could be simplified for clarity and conciseness. A succinct title would not only improve readability but also align better with standard academic writing practices. Response: We have shortened the title of Section 3.1(corresponding to the original manuscript as Section 2.1) to improve readability. 4. Fig. 4 lacks clarity regarding the model’s inputs and outputs, which are critical for understanding the workflow. It is recommended that the authors refine the figure by explicitly labeling these elements or adding a brief explanatory note. This improvement will significantly enhance the figure’s utility for readers. Response: Thank you for the suggestions. We have used lines of different colors for inputs and outputs in Figure 4 and added short notes. 5. There are typographical errors in the manuscript that need to be corrected. For example, “RuLU” should be replaced with the correct term “ReLU.” Additionally, Fig. 2 should be carefully reviewed for similar errors or inconsistencies to ensure the accuracy and professionalism of the presentation. Response: We have corrected some errors in Figure 2, making our paper more accurate and professional! Attachments Attachment Submitted filename: Response to Reviewers.docx https://doi.org/10.1371/journal.pone.0322323.r003
19 Mar 2025 Decision Letter - Zeeshan Ahmad, Editor Reconstruction of Missing Data in Transferred Generative Adversarial Networks with Small Sample Data PONE-D-24-51993R1 Dear Dr. Chen, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Zeeshan Ahmad Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author Reviewer #1: (No Response) Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: (No Response) Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: (No Response) Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: (No Response) Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: (No Response) Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: (No Response) Reviewer #2: The revisions made to this paper have significantly enhanced its quality. The authors have addressed previous concerns effectively, and the manuscript now demonstrates clarity, coherence, and rigor. I have no further comments and consider the paper ready for publication. ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean? ). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy . Reviewer #1: No Reviewer #2: No ******** https://doi.org/10.1371/journal.pone.0322323.r004
Formally Accepted
Acceptance Letter - Zeeshan Ahmad, Editor PONE-D-24-51993R1 PLOS ONE Dear Dr. Chen, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Dr. Zeeshan Ahmad Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0322323.r005

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .