New Frontiers in Graph Learning (GLFrontiers)

NeurIPS Workshop 2023

Call for Papers

Submission deadline: Saturday, Sept 30, 2023 (Anywhere on Earth)

Submission site (OpenReview): NeurIPS 2023 GLFrontiers Workshop

Author notification: Oct 27, 2023 (Anywhere on Earth)

Camera ready deadline: Dec 8, 2023 (Anywhere on Earth)

Workshop (in person): Friday, Dec 15, 2023

FAQ

  • GLFrontiers is a non-archival workshop. If you have concurrent submissions to other venues, please feel free to submit to our workshop as well.
  • Suppose your submission will present at the NeurIPS main conference, we suggest the author do not submit to the workshop, as it leads to unnecessary redundancy at the venue. If your submission has been rejected by the NeurIPS main conference, we welcome you to submit to our workshop.
  • You may think of the full-length research paper as a standard conference submissions. Meanwhile, we highly welcome the 6-page short submissions as well; for example, if you have worked on exciting ideas but the paper is not fully finished (e.g., missing some baselines or experiments), or the idea itself does not take a full 9 pages to describe (e.g., a new training strategy, loss function, or initialization that works surprisingly well).

The workshop will be held fully in person at the New Orleans Convention Center, as part of the NeurIPS 2023 conference. We also plan to offer livestream for the event, and more details will come soon.

We welcome submissions regarding the new frontiers of graph learning, including but not limited to:

  • Foundation models for graphs and relational data: Innovative ideas and perspectives in building generic foundation models for the ubiquitous graph-structured data and relational data. For example, there are recent attempts in building foundation models for molecule graphs, drug pairs and proteins. The foundation large language models also bring new opportunities for interacting with structural data with language interface.

  • Graph/Knowledge enhanced LLMs: Ideas and proofs-of-concept in using structured knowledge to enhance the capability of LLMs in returning factual, private and/or domain-specific answers. Examples include retrieval augmented LLMs, Knowledge-enhanced LLMs and improved LLMs reasoning.

  • Graph AI for science: Proofs-of-concept and perspectives in discovering graph and relational data in various scientific domains, and solving the problems with graph AI and machine learning. Recent works have achieved state-of-the-art using graph learning in sciences such as chemistry, biology, environmental science, physics and neuroscience.

  • Multimodal learning with Graphs: Graphs can often be leveraged in the multimodal learning context to provide rich information and complement visual / text data. For example, recent works have utilized scene graph in combination with diffusion models for more faithful image generation. Multimodal graph learning is also demonstrated to be critical in learning gene embeddings for multi-omics and multi-tissue data. A joint model of graph and text further improves state-of-the-art in the domain of molecules, logical reasoning and QA.

  • Trustworthy graph learning: Trustworthiness of graph learning has been a rapidly developing field to ensure that the developed graph learning models can align with human values, and applicable in mission-critical use cases. We welcome various aspects of trustworthy graph representation learning, including adversarial robustness, explainable ML, ML fairness, causal inference, privacy, federated learning etc.

We welcome both short research papers of up to 6 pages (excluding references and supplementary materials), and full-length research papers of up to 9 pages (excluding references and supplementary materials). All accepted papers will be presented as posters. We plan to select 10 papers for short oral presentations and 1-2 papers for the outstanding paper award.

All submissions must use the NeurIPS template. We do not require the authors to include the checklist in the template. Submissions should be in .pdf format, and the review process is double-blind—therefore the papers should be appropriately anonymised. Previously published work (or under-review) is acceptable.

For accepted papers, please use the following NeurIPS GLFrontiers style file for the camera ready submission, which has the correct notice at the first page of your paper. Please use the option \usepackage[final]{neurips_glfrontiers_2023} in your main text file. Please upload your camera ready version via making a revision at OpenReview.

Should you have any questions, please reach out to us via email:
glfrontiers@googlegroups.com