Accurate bundle matching and generation via multitask learning with partially shared parameters

Hyunsik Jeon; Jun-Gi Jang; Taehun Kim; U. Kang

doi:10.1371/journal.pone.0280630

Peer Review History

Original SubmissionNovember 3, 2022
25 Nov 2022 Decision Letter - Sathishkumar V E, Editor PONE-D-22-30342Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared ParametersPLOS 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 Jan 09 2023 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, Sathishkumar V E 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 Jung-Hun Foundation. The Institute of Engineering Research at Seoul National University provided research facilities for this work. The ICT at Seoul National University provides research facilities for this study." 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. 4. In your Data Availability statement, you have not specified where the minimal data set underlying the results described in your manuscript can be found. PLOS defines a study's minimal data set as the underlying data used to reach the conclusions drawn in the manuscript and any additional data required to replicate the reported study findings in their entirety. All PLOS journals require that the minimal data set be made fully available. For more information about our data policy, please see http://journals.plos.org/plosone/s/data-availability. "Upon re-submitting your revised manuscript, please upload your study’s minimal underlying data set as either Supporting Information files or to a stable, public repository and include the relevant URLs, DOIs, or accession numbers within your revised cover letter. For a list of acceptable repositories, please see http://journals.plos.org/plosone/s/data-availability#loc-recommended-repositories. Any potentially identifying patient information must be fully anonymized. Important: If there are ethical or legal restrictions to sharing your data publicly, please explain these restrictions in detail. Please see our guidelines for more information on what we consider unacceptable restrictions to publicly sharing data: http://journals.plos.org/plosone/s/data-availability#loc-unacceptable-data-access-restrictions. Note that it is not acceptable for the authors to be the sole named individuals responsible for ensuring data access. We will update your Data Availability statement to reflect the information you provide in your cover letter. 5. Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. [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: No 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: 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: No 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 submission the authors present two methodologies for bundle recommendation: one for bundle creation and another for bundle recommendation (matching). Their work is intuitive and original, especially w.r.t the PreMix module. However, a number of issues need to be addressed prior to accepting this manuscript for publication. 1. Please, organize your manuscript better. Avoid asking too many questions and use a more natural and scientific language flow. In this respect, I believe Figure 1(a) should be placed near the results section of the manuscript, while Figure 1(b) (the intuition for your work) should remain at its place. Additionally, problem definition should be a different section, preceded by the related works sections. Finally proofread your manuscript for the correct use of the english language and for correcting typos (eg “performance” instead of “performances” on line 23). 2. The analysis of lines 168-188 (different item & bundle preferences for each users) is not convincing, it it does not examine the intra-bundle cosine similarities of items. 3. Eq (2) should be explained in more detail 4. The adaptive gated preference mixture is among the top contribution of this manuscript, therefore it needs to be analyzed much more, instead of just laying out equations. For example what is the intuition behind the input of the FNN in Eq. 3. Why is this form the most suitable? 5. Even though a leave-one-out cross-validation seems to have been considered in the experiments (lines 334-348) w.r.t to bundle matching, it appears that this is not the case for bundle generation, since it is reported that a random 10% of the bundles has been singled out as a test set. Additionally, the statistical significance of the reported results on Tables 3-5 is not assessed. 6. The concluding section is too thin. It should at least report the main points and the “lessons learned” from the overall approach. Reviewer #2: The manuscript is well written with supporting results and explanations The literature has to be strongly updated with some relevant and recent papers focused on the fields dealt with in the manuscript and making related works as a separate section will be more appropriate for the readers. Any hyperparamter search done? Authors set default hyperparaters suggested by the articles in reference. Provide explanation regarding this. Why recall@k and nDCG@k is used as a performance metric? ****** 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: Yes: Usha Moorthy ******** [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.0280630.r001
Revision 1
3 Jan 2023 Author Response We would like to thank the reviewers for their high quality reviews and constructive comments. Below, we summarize how we addressed the reviewers’ requirements. 1. Reviewer 1. • (R1-1) Please organize your manuscript better. Avoid asking too many questions and use a more natural and scientific language flow. In this respect, I believe Fig 1(a) should be placed near the results section of the manuscript, while Fig 1(b) (the intuition for your work) should remain at its place. Additionally, problem definition should be a different section, preceded by the related works sections. Finally proofread your manuscript for the correct use of the english language and for correcting typos (e.g., performance instead of performances on line 23). – (A1-1) We replaced the interrogative sentences with other scientific sentences in the section on the proposed method (lines 195-197 and lines 262-263) except in the overview where we provide the research question of this work. We removed Fig 1(a) because it would be redundant if placed near the results section, while Fig 1(b) remained in its place as you recommended. We separated the sections of problem definition and related works in lines 56-120. We also reviewed the overall manuscript to correct typos. • (R1-2) The analysis of lines 168-188 (different item & bundle preferences for each users) is not convincing, it does not examine the intra-bundle cosine similarities of items. – (A1-2) Our goal of the analysis in the section on bundle matching is to compare user preferences for items and bundles. We extract the representative vector of each bundle as the average of the vectors of the constituent items regardless of the intra-bundle relationships of the items. For instance, if a bundle mainly consists of action games, the bundle’s vector is computed to represent the action games by averaging the vectors of the constituent items. Furthermore, each user’s preference is computed as the averaged vector of items or bundles that the user interacted with. Thus, our analysis provides dissimilar preference patterns of users for items and bundles by comparing the user interactions for items and bundles. We clearly provided the description in lines 184-186 of the bundle matching section. • (R1-3) Equation (2) should be explained in more detail. – (A1-3) Equation (2) denotes the average of embeddings of the observed bundles in $\\ddot{\\mathbf{r}}_b$. We provided a more detailed description of the equation in lines 212-214 of the bundle matching section. • (R1-4) The adaptive gated preference mixture is among the top contribution of this manuscript, therefore it needs to be analyzed much more, instead of just laying out equations. For example, what is the intuition behind the input of the FNN in Equation (3)? Why is this form the most suitable? – (A1-4) The intuition behind the usage of the FNN is to extract more complicated non-linear features from the gated preference mixture. We also constrain the hidden dimension of the neural network to be smaller than the input and output dimensions to effectively extract only meaningful information. We provided the intuition and the description of the FNN in lines 218-222 of the bundle matching section. • (R1-5) Even though a leave-one-out cross-validation seems to have been considered in the experiments (lines 334-348) w.r.t bundle matching, it appears that this is not the case for bundle generation, since it is reported that a random 10% of the bundles has been singled out as a test set. Additionally, the statistical significance of the reported results on Tables 3-5 is not assessed. – (A1-5) We use all user-bundle interactions of the selected 10% bundles as the held-out dataset for bundle generation to evaluate the generation performance on bundles that have not been observed in the training process. As you mentioned, the leave-one-out setting is used only for the bundle matching. We provided a more detailed description of the experimental process in lines 345-346 of the experiments section. In addition, we conduct each experiment at least three times and report the average to secure the statistical significance. We provided the description in line 359 of the experiments section. • (R1-6) The concluding section is too thin. It should at least report the main points and the lessons learned from the overall approach. – (A1-6) We learned that each idea in our proposed method helps improve the performance. Especially, the multi-task learning-based approach significantly improves performance because matching and generation are highly related tasks. We provided the lessons learned from the experimental results of our proposed method in lines 448-453 of the conclusion section. 2. Reviewer 2. • (R2-1) The literature has to be strongly updated with some relevant and recent papers focused on the fields dealt with in the manuscript. – (A2-1) We added the following related and recent papers to the manuscript. ∗ J. Ma, C. Zhou, P. Cui, H. Yang, and W. Zhu, “Learning disentangled representations for recommendation,” in NeurIPS, 2019. ∗ Q. Deng, K. Wang, M. Zhao, Z. Zou, R. Wu, J. Tao, C. Fan, and L. Chen, “Personalized bundle recommendation in online games,” in CIKM. ACM, 2020. ∗ J. Chang, C. Gao, X. He, D. Jin, and Y. Li, “Bundle recommendation and generation with graph neural networks,” TKDE, 2021. ∗ Z. Wang, Y. Zhu, H. Liu, and C. Wang, “Learning graph-based disentangled representa- tions for next POI recommendation,” in SIGIR. ACM, 2022. ∗ J. Cao, X. Lin, X. Cong, J. Ya, T. Liu, and B. Wang, “Disencdr: Learning disentangled representations for cross-domain recommendation,” in SIGIR. ACM, 2022. • (R2-2) Making related works as a separate section will be more appropriate for the readers. – (A2-2) We separated the sections of problem definition and related works in lines 56-120. • (R2-3) Any hyperparamter search done? Authors set default hyperparaters suggested by the articles in reference. Provide explanation regarding this. – (A2-3) We denoted the search space of hyperparameters and explained that we selected the best among the candidates in lines 360-364 of the experiments section. • (R2-4) Why recall@k and nDCG@k is used as a performance metric? – (A2-4) The two metrics are the most widely used metrics for evaluating recommendation accuracy. We added the description for the evaluation metrics in lines 338-339 of the experi- ments section. Attachments Attachment Submitted filename: rebuttal_letter.pdf https://doi.org/10.1371/journal.pone.0280630.r002
5 Jan 2023 Decision Letter - Sathishkumar V E, Editor Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters PONE-D-22-30342R1 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, Sathishkumar V E 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 #2: (No Response) ******** 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 #2: (No Response) ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #2: (No Response) ****** 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 #2: (No Response) ****** 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 #2: (No Response) ****** 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 #2: (No Response) ****** 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 #2: Yes: Usha Moorthy ******** https://doi.org/10.1371/journal.pone.0280630.r003
Formally Accepted
9 Jan 2023 Acceptance Letter - Sathishkumar V E, Editor PONE-D-22-30342R1 Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameters 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. Sathishkumar V E Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0280630.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 .