Learning from conflicting data with hidden contexts

Tianren Zhang, Yizhou Jiang, Xin Su, Shangqi Guo, Chongkai Gao, Feng Chen

Keywords: Conflicting data, hidden contexts, subjective learning, multi-domain learning

TL;DR: We formulate the problem of learning from conflicting data with hidden contexts and propose a subjective learning framework to tackle this problem.

Abstract: Classical supervised learning assumes a stable relation between inputs and outputs. However, this assumption is often invalid in real-world scenarios where the input-output relation in the data depends on some hidden contexts. We formulate a more general setting where the training data is sampled from multiple unobservable domains, while different domains may possess semantically distinct input-output maps. Training data exhibits inherent conflict in this setting, rendering vanilla empirical risk minimization problematic. We propose to tackle this problem by introducing an allocation function that learns to allocate conflicting data to different prediction models, resulting in an algorithm that we term LEAF. We draw an intriguing connection between our approach and a variant of the Expectation-Maximization algorithm. We provide theoretical justifications for LEAF on its identifiability, learnability, and generalization error. Empirical results demonstrate the efficacy and potential applications of LEAF in a range of regression and classification tasks on both synthetic data and real-world datasets.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning