DAO-CP: Data-Adaptive Online CP decomposition for tensor stream

Sangjun Son; Yong-chan Park; Minyong Cho; U. Kang

doi:10.1371/journal.pone.0267091

Peer Review History

Original SubmissionDecember 13, 2021
11 Feb 2022 Decision Letter - Ning Cai, Editor PONE-D-21-39294DAO-CP: Data-Adaptive Online CP Decomposition for Tensor StreamPLOS ONE Dear Dr. Kang, 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 Mar 28 2022 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, Ning Cai, Ph.D. 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. We note that the grant information you provided in the ‘Funding Information’ and ‘Financial Disclosure’ sections do not match. When you resubmit, please ensure that you provide the correct grant numbers for the awards you received for your study in the ‘Funding Information’ section. 3. Thank you for stating the following financial disclosure: “This work was supported by the National Research Foundation of Korea(NRF) funded by MSIT(2019R1A2C2004990). The Institute of Engineering Research and ICT at Seoul National University provided research facilities for this work.” Please state what role the funders took in the study. If the funders had no role, please state: "The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript." If this statement is not correct you must amend it as needed. Please include this amended Role of Funder statement in your cover letter; we will change the online submission form on your behalf. [Note: HTML markup is below. Please do not edit.] 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: Partly Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: N/A Reviewer #2: N/A ****** 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: Yes Reviewer #2: Yes ****** 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: Yes ****** 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: In this paper, the authors propose DAO–CP, an accurate and efficient online CP decomposition method, which adapts to data changes. DAO–CP tracks local error norms of the tensor streams, detecting a change point of the error norms. It then chooses the best strategy depending on the degree of changes to balance the trade-off between speed and accuracy. I have the following comments for this paper: 1. The format of this article is not standard. If you use word template, please align left and right. 2. The writting is bad. I am not so sure about your contributions after reading the paper. your contribution is just the rules to detect the check points with local error norm? You use alternating minimization for DAO-CP. 3. Due to your method is data adaptive, it is better to give an depict of the data, which may affect the computation of local error norm? 4. It may be better to add some comparisons with some existing online methods. Reviewer #2: Overall the paper is fairly easy to follow, and is consistent in notation, terminology, and theme as many other works in this area. Since the streaming decomposition method is basically DTD, the primary technical contribution of the paper is the logic for adapting the decomposition based on error thresholds when the current factor matrices do not well represent the new tensor data. Their logic for the adaptation process is reasonable, but does include some hyperparameters that would require tuning for each new problem. I think that contribution is significant enough to merit publication, but I do have several comments outlined in the attached review. ****** 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. Attachments Attachment Submitted filename: review.pdf https://doi.org/10.1371/journal.pone.0267091.r001
Revision 1
22 Mar 2022 Author Response We would like to thank the reviewers for their high quality reviews and constructive comments. We hope our revision has successfully addressed all your concerns. Below, we typed the content in 'rebuttal_letter.pdf' for just in case. Reviewer 1. • (R1-1) The format of this article is not standard. If you use word template, please align left and right. – (A1-1) We corrected the format of the article according to reviewer’s comments. • (R1-2) The writting is bad. I am not so sure about your contributions after reading the paper. your contribution is just the rules to detect the check points with local error norm? You use alternating minimization for DAO-CP. – (A1-2) We revised the paper to clearly highlight the contributions of our work (lines 29-35). Our main contributions are summarized as follows: (1) We employ z-score analysis to rapidly detect the change points of streaming tensors. (2) We introduce re-decomposition process to balance the trade-off between accuracy and speed. (3) We use complementary matrices and simplify the objective function from DTD in order to reduce the redundant computations in CP-ALS optimization. • (R1-3) Due to your method is data adaptive, it is better to give an depict of the data, which may affect the computation of local error norm? – (A1-3) We further included description of the data in Experiments section (lines 308-326). For example, Fig. 6 illustrates how our proposed method adapts to the Sample Video dataset; DAO-CP achieves the state-of-the-art accuracy when an object starts moving or a scene changes in the data. • (R1-4) It may be better to add some comparisons with some existing online methods. – (A1-4) We included another recent paper called “Identifying and Alleviating Concept Drift in Streaming Tensor Decomposition (R. Pasricha et al., 2019),” and compared it with our proposed method in Related Works section (lines 116-125). Reviewer 2. • (R2-1) The approach does not appear to be appropriate for infinite data streams because by my reading of Eq. 12, all prior time steps are included in first term defining the objective function for the optimization problem solved each time step. Typically, authors use an exponential down-weighting of older and older time steps to effectively truncate the prior temporal data that must be stored and manipulated. Furthermore, this can be seen in Lemma 2, showing a cost proportional to I1old, which would grow linearly in time. It seems to me this would be straightforward improvement, so I wonder why the authors chose not to do this. • (R2-2) It is also unusual that the authors update the factor matrix rows corresponding to the prior time steps (see first line after Eq. 12). Typically, authors use a 2-stage process where they update the temporal mode keeping the non-temporal mode fixed (which means the rows of the factor matrix corresponding to old time steps do not change), and then update the nontemporal modes using the newly updated temporal factor. This saves computational cost, so again, I wonder why the authors chose not to do this. – (A2-1 and A2-2) We choose to consider all prior time steps and update the whole temporal factors to further increase the accuracy of decomposition. If the previous temporal factors are not updated, they harm the accuracy of method whenever there is a change of theme because they are optimized only for the previous theme of the data. Thus, even though our proposed method requires a time cost growing linearly, it significantly increases the decomposition accuracy (Fig. 4), and shows promising speeds comparable to state-of-the-art methods for all the datasets (Fig. 5). We included additional explanation to justify our method in Proposed Method section (lines 190-193). • (R2-3) The authors should make it clear their approach does not adapt the rank of the CP decomposition, nor add or remove factors. They should discuss how their method compares to the concept drift approach in SeekAndDestroy (Parischa, Gujral, Papelaxakis, 2019). – (A2-3) Unlike SeekAndDestroy, DAO-CP does not require estimating the actual rank numbers, but only tracks the difference of them using local error norms. This technique enables DAO-CP to rapidly capture the change points of theme without adding or removing factors. We included additional comparisons between DAO-CP and SeekAndDestroy in Related Works section (lines 116-125). • (R2-4) The computational results compare to running the full CP decomposition each time step using the entire streamed tensor to that point, which isn’t necessary. A more fair comparison would be just running full CP at the end of the stream, since running it at intermediate time steps does not provide any new information. – (A2-4) We compared the computation results between DAO-CP and full CP for each time step because we aim to answer how well DAO-CP performs for time-evolving tensors. In Fig. 6, we find that DAO-CP outperforms full CP in terms of local error norm whenever refinement or split process is executed. If we run full CP only at the end of the stream, we cannot compare the local error norm between DAO-CP and full CP at intermediate time steps. Attachments Attachment Submitted filename: rebuttal_letter.pdf https://doi.org/10.1371/journal.pone.0267091.r002
4 Apr 2022 Decision Letter - Ning Cai, Editor DAO-CP: Data-Adaptive Online CP Decomposition for Tensor Stream PONE-D-21-39294R1 Dear Dr. Kang, 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 for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, 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, Ning Cai, Ph.D. Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #3: All comments have been addressed Reviewer #4: 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 #3: Yes Reviewer #4: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #3: Yes Reviewer #4: 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 #3: Yes Reviewer #4: 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 #3: Yes Reviewer #4: 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 #3: (No Response) Reviewer #4: In this paper, authors proposed online CP decomposition method which adapts to data changes. The method can better balance the trade-off of the tensor streams between speed and accuracy. The results of this paper is interesting and important. ****** 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 #3: No Reviewer #4: No https://doi.org/10.1371/journal.pone.0267091.r003
Formally Accepted
6 Apr 2022 Acceptance Letter - Ning Cai, Editor PONE-D-21-39294R1 DAO-CP: Data-Adaptive Online CP Decomposition for Tensor Stream Dear Dr. Kang: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. 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 plosone@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. Ning Cai Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0267091.r004

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 .