Abstract Diagrammatic Reasoning with Multiplex Graph Networks
- Submitting institution
-
University of Cambridge
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 8993
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- ICLR
- First page
- 1
- Volume
- -
- Issue
- -
- ISSN
- -
- Open access status
- -
- Month of publication
- -
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- -
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper was published in ICLR, one of the top conferences for Artificial Intelligence and Machine learning. This paper contributes to the field of machine learning for reasoning, and its originality lies in applying graph neural networks for reasoning with multiple objects that are distributed in different diagrams. This paper achieved state-of-the-art results (by a very significant margin) on two datasets of visual reasoning at the time of submission. As the paper was recently published, it is still too early to judge its impact.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -