Call for Papers

Learning on Graphs Conference, 2022

Table of Contents

Call For Papers

We welcome papers from areas broadly related to learning on graphs and geometry. The LoG conference has a proceedings track with papers published in Proceedings for Machine Learning Research (PMLR) and a non-archival extended abstract track. Papers can be submitted through OpenReview using our LaTeX style files (download or Overleaf template). Papers are reviewed double-blind, and reviews are rated for their quality by authors and area chairs. The top reviewers receive high monetary rewards, as described below.

Important Dates

(All deadlines are “Anywhere On Earth”.)

  • September 9th, 2022: Abstract Submission Deadline (both Tracks)

  • September 16th, 2022: Submission Deadline (both Tracks)

  • October 27th, 2022: 2 Week Paper Revision Period Starts

  • November 7rd, 2022: Paper Revision Period Ends

  • November 24th, 2022: Final Decisions Released

  • November 30th, 2022: Camera Ready Deadline

  • December 9th, 2022: Conference Starts (Virtual, free to attend)

Proceedings Track

Accepted proceedings papers will be published in the Proceedings for Machine Learning Research (PMLR) and are eligible for our proceedings spotlights. Full proceedings papers can have up to 9 pages with unlimited pages for references and appendix.

Submitted papers cannot be already published or under review in any other archival venue. Upon acceptance of a paper, at least one of the authors must join the conference, or their paper will not be included in the proceedings.

Extended Abstract Track

Extended abstracts can be up to 4 pages with unlimited pages for references and appendix. The top papers are chosen for our abstract spotlights. Authors of accepted extended abstracts (non-archival submissions) retain full copyright of their work, and acceptance to LoG does not preclude publication of the same material at another venue. Also, submissions that are under review or have been recently published are allowed for submission. Authors must ensure that they are not violating any other venue dual submission policies.

What qualifies as an extended abstract? Extended abstracts need to provide novel insights or enable future research with novel insights. This can be through presenting new ideas/ways of thinking, leading to insightful discussion and feedback, or dissemination of new valuable resources. We also welcome “non-traditional research artifacts” as submissions to the extended abstract track, such as papers highlighting novel datasets, insightful negative results, exciting preliminary results that warrant rapid dissemination, or reproducibility studies.

Subject Areas

The following is a summary of LoG’s focus, which is not exhaustive. If you doubt that your paper fits the venue, feel free to contact pcs@logconference.org or logconference@googlegroups.com!

  • Expressive Graph Neural Networks
  • GNN architectures (transformers, new positional encodings, …)
  • Equivariant architectures
  • Statistical theory on graphs
  • Causal inference (structural causal models, …)
  • Algorithmic reasoning
  • Geometry processing
  • Robustness and adversarial attacks on graphs
  • Combinatorial Optimization and Graph Algorithms
  • Graph Kernels
  • Graph Signal Processing/Spectral Methods
  • Graph Generative Models
  • Scalable Graph Learning Models and Methods
  • Graphs for Recommender Systems
  • Graph/Geometric ML for Computer Vision
  • Knowledge Graphs
  • Graph ML for Natural Language Processing
  • Graph/Geometric ML for Molecules (molecules, proteins, drug discovery, …)
  • Graph ML for Security
  • Graph ML for Health
  • Graph/Geometric ML for Physical sciences
  • Graph ML Platforms and Systems
  • Self-supervised learning on graphs
  • Trustworthy graph ML (fairness, privacy, …)
  • Graph/Geometric ML Infrastructures (datasets, benchmarks, libraries, …)

Reviewer Rewards

Area chairs rate the quality of each review in terms of “constructivism.” The 20 highest-rated reviewers will receive an expected reward of $1500 funded by our generous sponsors. The exact number of reviewers that receive an award and the award amount is subject to change and might increase if more sponsor money is leftover than expected. The top reviewer (who is willing to do so) is invited to hold a talk about reviewing at the conference.

If you wish to become a reviewer and are qualified (e.g., by having published graph or geometry papers), you can sign up via this form.

Review Process

Submissions will be double-blind: reviewers cannot see author names when conducting reviews, and authors cannot see reviewer names. We use OpenReview to host papers and allow for public discussions that can be seen by all; comments that are posted by reviewers will remain anonymous. However, program chairs can know the reviewers’ identities and reviewers with particularly low-quality reviews can be excluded from future review processes (the review was flagged as low-quality and discussed by multiple area chairs and program chairs).

  1. Submissions are uploaded on OpenReview, publicly available, and official reviews are anonymous. Anybody can post comments that are publicly visible, or restrict visibility to e.g. reviewers or area chairs. We also recommend using Anonymous GitHub for authors to anonymize GitHub repositories.
  2. Authors can participate in the discussion about their paper at any time.
  3. Full reviews are posted by October 20th, when the paper revision period starts. In the 2-week paper revision period, authors are allowed to adjust their paper again.
  4. After November 3rd, there will be an internal discussion period amongst reviewers and ACs with the aim of summarising the review process, after which acceptance decisions are made.
  5. Accepted papers will be deanonymized (rejected ones can opt-out) after the notification on Nov 24th.

Preprint Policy

The existence of non-anonymous preprints (on arXiv or other online repositories, personal websites, social media) will not result in rejection. Authors may submit anonymized work to LoG that is already available as a preprint (e.g., on arXiv) without citing it.