PONE-D-20-21179

Learning temporal attention in dynamic graphs with bilinear interactions

PLOS ONE

Dear Dr. Augusta,

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 Nov 19 2020 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: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

We look forward to receiving your revised manuscript.

Kind regards,

Chi Ho Yeung

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. Thank you for stating the following in the Financial Disclosure section:

2BK is funded by the Mila internship, the Vector Institute, the University of Guelph and DARPA (FA8750-17-C-0115). CA is funded by the University of Saskatchewan. GWT is funded by CIFAR, Canada Research Chairs and the University of Guelph. For a portion of time during this study, GWT received salary from Google. The views, opinions and/or findings expressed are those of the authors and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S. Government. The authors also acknowledge equipment support from Canada Foundation for Innovation. Resources used in preparing this research were provided, in part, by the Province of Ontario, the Government of Canada through CIFAR, and companies sponsoring the Vector Institute: " ext-link-type="uri" xlink:type="simple">http://www.vectorinstitute.ai/#partners."

We note that one or more of the authors are/were employed by a commercial company: Google.

2.1. Please provide an amended Funding Statement declaring this commercial affiliation, as well as a statement regarding the Role of Funders in your study. If the funding organization did not play a role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript and only provided financial support in the form of authors' salaries and/or research materials, please review your statements relating to the author contributions, and ensure you have specifically and accurately indicated the role(s) that these authors had in your study. You can update author roles in the Author Contributions section of the online submission form.

Please also include the following statement within your amended Funding Statement.

“The funder provided support in the form of salaries for authors [insert relevant initials], but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of these authors are articulated in the ‘author contributions’ section.”

If your commercial affiliation did play a role in your study, please state and explain this role within your updated Funding Statement.

2.2. Please also provide an updated Competing Interests Statement declaring this commercial affiliation along with any other relevant declarations relating to employment, consultancy, patents, products in development, or marketed products, etc.  

Within your Competing Interests Statement, please confirm that this commercial affiliation does not alter your adherence to all PLOS ONE policies on sharing data and materials by including the following statement: "This does not alter our adherence to  PLOS ONE policies on sharing data and materials.” (as detailed online in our guide for authors http://journals.plos.org/plosone/s/competing-interests) . If this adherence statement is not accurate and  there are restrictions on sharing of data and/or materials, please state these. Please note that we cannot proceed with consideration of your article until this information has been declared.

Please include both an updated Funding Statement and Competing Interests Statement in your cover letter. We will change the online submission form on your behalf.

Please know it is PLOS ONE policy for corresponding authors to declare, on behalf of all authors, all potential competing interests for the purposes of transparency. PLOS defines a competing interest as anything that interferes with, or could reasonably be perceived as interfering with, the full and objective presentation, peer review, editorial decision-making, or publication of research or non-research articles submitted to one of the journals. Competing interests can be financial or non-financial, professional, or personal. Competing interests can arise in relationship to an organization or another person. Please follow this link to our website for more details on competing interests: http://journals.plos.org/plosone/s/competing-interests

3. We noted in your submission details that a portion of your manuscript may have been presented or published elsewhere.

" The data have been published elsewhere and are publicly available. We do not create data, but rather use these two publicly available data sets.

Madan A, Cebrian M, Moturu S, Farrahi K, et al. Sensing the \\health state" of a

community. IEEE Pervasive Computing. 2012;11(4):36{45."

Please clarify whether this [conference proceeding or publication] was peer-reviewed and formally published. If this work was previously peer-reviewed and published, in the cover letter please provide the reason that this work does not constitute dual publication and should be included in the current manuscript.

[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: 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: 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: The paper is interesting and well written. They have good results and they are presented well.

Just a few minor points:

1) The task you are focusing on is event prediction, but you don't really state it clearly (casually mentioned in the DyRep backgroup part). Please state it more clearly for clearity.

2) There is an issue with the figures, they are in the end of the paper instead of embedded in it as I assume the authors intended.

3) minor typo in dimension, line 205

Reviewer #2: The manuscript focuses on reasoning dynamic graph data and proposed a model called Latent Dynamic Graph (LDG). The authors first introduced Neural Relational Inference (NRI) into the existing DyREP [1] model for link prediction on dynamic graphs. Then they replace the concatenation based layers in DyREP with bilinear layers. The experiment result shows that in many cases, during model training, using NRI, i.e. discarding human-specified graph and letting the model capture the graph structure implicitly, can be better than using human-specified graph. Moreover, bilinear layers are superior to simple concatenation in capturing pairwise interaction.

Strength:

1. The combination of NRI and DyREP makes the learning process independent of human-specified graph, and the proposed model LDG can learn a similar attention structure to the ground truth association graph, as stated in Fig. 8. It is novel to apply this method to improve the DyREP model.

2. By introducing the bilinear encoder and the bilinear intensity function, the performance of LDG is better than baseline method DyREP in almost all cases stated in Table 3.

Weakness:

1. The number of baseline models is too small. It is better to include more results of other models doing dynamic link prediction on the same dataset. In DyREP’s paper, Know-Evolve [2], DynGEM [3], GraphSage [4] and GAT [5] are used as baselines. It might strengthen this submission’s contributions if the authors could compare one or two more baselines. It might strengthen this submission’s contributions if the authors could compare one or two more baselines. Besides, a recent model architecture for link forecasting on dynamic and multi-relational graphs is proposed in [6], which is missing in the related work.

2. To show the superiority of bilinear layers, it is better to do an ablation study regarding it. For example, the authors can first give the experiment result of LDG by maintaining concatenation in equation (8), (10), (12). Then replace these concatenation with bilinear layers in equation (8), (10), (12), and report the experiment result as well.

3. Similar to point 2, the authors can also do another ablation study to show how NRI affects the performance. For example, the authors can first give the experiment result of LDG by maintaining concatenation in equation (8), (10), (12), and then compare this result with the performance of DyREP. To summarize, I recommend this paper to be accepted. However, there is still a lot of work to do to improve it. The most important point is to compare LDG with more models

from different angles.

4. Current datasets contain only thousands of nodes, which might be impractical for real applications. The reviewers understand that the authors mainly aim to compare and beat the DyRep model, therefore, it would be great if the authors could implement and compare their methods on larger datasets, but not necessary.

[1] DYREP: LEARNING REPRESENTATIONS OVER DYNAMIC GRAPHS

[2] Know-evolve: Deep temporal reasoning for dynamic knowledge graphs

[3] Dyngem: Deep embedding method for dynamic graphs

[4] Inductive representation learning on large graphs

[5] Graph attention networks.

[6] Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs

**********

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.

Learning temporal attention in dynamic graphs with bilinear interactions

PONE-D-20-21179R1

Dear Dr. Augusta,

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,

Chi Ho Yeung

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

The authors have well addressed the questions raised by both reviewers, I therefore recommend the manuscript to be accepted for publication.

Reviewers' comments: