Geometric matrix completion with recurrent multi-graph neural networks
- Submitting institution
-
Imperial College of Science, Technology and Medicine
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 2263
- Type
- E - Conference contribution
- DOI
-
-
- Title of conference / published proceedings
- NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems
- First page
- 3700
- Volume
- 2017-December
- Issue
- -
- ISSN
- 1049-5258
- Open access status
- Deposit exception
- Month of publication
- December
- Year of publication
- 2017
- 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
- 1
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The paper extended graph deep learning models to graph products and proposed the first recommender system algorithm based on graph CNNs, with state-of-the-art performance. The method was patented (Application 15/952,984) and licensed to spinoff FabulaAI, acquired by Twitter (https://blog.twitter.com/en_us/topics/company/2019/Twitter-acquires-Fabula-AI.htmli). The work led to a keynote at Graph Signal Processing 2018 (https://gsp18.epfl.ch/program). The first author Monti was invited for an internship at Google and co-founded Fabula AI. NIPS 2017 acceptance rate: 21%/3240.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
