Learning Task-Relevant Features via Contrastive Input MorphingDownload PDF

28 Sept 2020 (modified: 05 May 2023)ICLR 2021 Conference Withdrawn SubmissionReaders: Everyone
Keywords: representation learning, spurious correlations, deep learning
Abstract: A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream classification task, without overfitting to spurious input features. Extracting task-relevant predictive information becomes particularly challenging for high-dimensional, noisy, real-world data. We propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream performance via a triplet loss. Empirically, we demonstrate the efficacy of our approach on various tasks which typically suffer from the presence of spurious correlations, and show that CIM improves the performance of other representation learning methods such as variational information bottleneck (VIB) when used in conjunction.
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
One-sentence Summary: We propose Contrastive Input Morphing (CIM), a representation learning framework that learns input-space transformations of the data to mitigate the effect of irrelevant input features on downstream predictive performance.
Reviewed Version (pdf): https://openreview.net/references/pdf?id=r7Z5yV8vDL
6 Replies

Loading