Neural Graph Reasoning: A Survey on Complex Logical Query Answering
Abstract: Complex logical query answering (CLQA) is a recently emerged task of graph machine learning that goes beyond simple one-hop link prediction and solves the far more complex task of multi-hop logical reasoning over massive, potentially incomplete graphs.
The task received significant traction in the community; numerous works expanded the field along theoretical and practical axes to tackle different types of complex queries and graph modalities with efficient systems.
In this paper, we provide a holistic survey of CLQA with a detailed taxonomy studying the field from multiple angles, including graph types (modality, reasoning domain, background semantics), modeling aspects (encoder, processor, decoder), supported queries (operators, patterns, projected variables), datasets, evaluation metrics, and applications.
Finally, we point out promising directions, unsolved problems and applications of CLQA for future research.
Submission Length: Long submission (more than 12 pages of main content)
Previous TMLR Submission Url: https://openreview.net/forum?id=MHaSHepq45&referrer=%5BAuthor%20Console%5D(%2Fgroup%3Fid%3DTMLR%2FAuthors%23your-submissions)
Changes Since Last Submission: AE's suggestion: I concur with a fellow reviewer regarding a concern: while the paper is positioned as a survey, it also presents the new concept of Neural Graph Databases (NGDBs), which somewhat gives it the characteristics of a position paper rather than a pure survey paper. The introduction of new concepts typically requires additional support and evidence. It may be more effective to focus on a single highlight in each paper. Therefore, I would kindly encourage the authors to consider dividing the paper into two separate submissions, with each one emphasizing a distinct aspect of the research.
Following AE's suggestion, the new version includes the following changes:
- We divided the paper into two separate parts, this submission is the survey aspect only, as requested by the action editor.
- We updated content of the survey to cover the most recent developments
Assigned Action Editor: ~Tao_Qin1
Submission Number: 2346
Loading