Towards Resolving Propensity Contradiction in Offline Recommender Learning

Authors: Yuta Saito, Masahiro Nomura

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on real-world datasets demonstrate that the proposed algorithm is superior to a range of existing methods both in rating prediction and ranking metrics in practical settings without MCAR data.
Researcher Affiliation Collaboration Yuta Saito1 , Masahiro Nomura2 1Cornell University 2Cyber Agent, Inc. ys552@cornell.edu, nomura masahiro@cyberagent.co.jp
Pseudocode Yes Algorithm 1 Domain Adversarial Matrix Factorization
Open Source Code Yes Our code is available at https://github.com/usaito/ijcai2022-adversarial-mf.
Open Datasets Yes Datasets. We use Yahoo! R33 and Coat4, which separately contain MNAR and MCAR datasets. 3http://webscope.sandbox.yahoo.com/ 4https://www.cs.cornell.edu/~schnabts/mnar/
Dataset Splits Yes We randomly selected 10% of the MNAR training set as the validation set, which is used to perform hyper-parameter tuning.
Hardware Specification No The paper describes experimental setups and training details but does not provide specific hardware specifications such as GPU or CPU models.
Software Dependencies No The paper does not explicitly state specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes Appendix B describes detailed experimental settings such as dataset description, evaluation metrics, and hyper-parameter tuning.