DeepAI AI Chat
Log In Sign Up

Understanding Instance-based Interpretability of Variational Auto-Encoders

by   Zhifeng Kong, et al.

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 [20], 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. [28], for VAEs. Finally, we evaluate VAE-TracIn on several real world datasets with extensive quantitative and qualitative analysis.


page 7

page 9

page 21

page 24

page 29

page 31

page 32

page 33


Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation

In unsupervised learning, variational auto-encoders (VAEs) are an influe...

Diagnosing Vulnerability of Variational Auto-Encoders to Adversarial Attacks

In this work, we explore adversarial attacks on the Variational Autoenco...

Unsupervised Learning of Neurosymbolic Encoders

We present a framework for the unsupervised learning of neurosymbolic en...

Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates

Among the most critical limitations of deep learning NLP models are thei...

Robust Disentanglement of a Few Factors at a Time

Disentanglement is at the forefront of unsupervised learning, as disenta...

Generative Models of Visually Grounded Imagination

It is easy for people to imagine what a man with pink hair looks like, e...

Statistical Model Criticism of Variational Auto-Encoders

We propose a framework for the statistical evaluation of variational aut...

Code Repositories


Official PyTorch implementation for "Understanding Instance-based Interpretability of Variational Auto-Encoders."

view repo