Understanding Instance-based Interpretability of Variational Auto-EncodersDownload PDF

21 May 2021, 20:45 (modified: 21 Jan 2022, 20:29)NeurIPS 2021 PosterReaders: Everyone
Keywords: Influence function, TracIn, instance-based interpretability, unsupervised learning, VAE
TL;DR: We investigate instance-based interpretability of variational auto-encoders.
Abstract: Instance-based interpretation methods have been widely studied for supervised learning methods as they help explain how black box neural networks predict. However, instance-based interpretations remain ill-understood in the context of unsupervised learning. In this paper, we investigate influence functions [Koh and Liang, 2017], a popular instance-based interpretation method, for a class of deep generative models called variational auto-encoders (VAE). We formally frame the counter-factual question answered by influence functions in this setting, and through theoretical analysis, examine what they reveal about the impact of training samples on classical unsupervised learning methods. We then introduce VAE- TracIn, a computationally efficient and theoretically sound solution based on Pruthi et al. [2020], for VAEs. Finally, we evaluate VAE-TracIn on several real world datasets with extensive quantitative and qualitative analysis.
Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.
Code: https://github.com/FengNiMa/VAE-TracIn-pytorch
13 Replies