Understanding Instance-based Interpretability of Variational Auto-Encoders
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 (1)
Similar Papers 제목 키워드 기반
Better Latent Spaces for Better Autoencoders
Autoencoders as tools behind anomaly searches at the LHC have the structural problem that they only work in one direction, extracting jets with higher complexity but not the other way around. To address this, we derive c…
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual sce…
Image GenerationMotion PlanningNatural Language UnderstandingCausal Intervention Framework for Variational Auto Encoder Mechanistic Interpretability
Mechanistic interpretability of deep learning models has emerged as a crucial research direction for understanding the functioning of neural networks. While significant progress has been made in interpreting discriminati…
DisentanglementSpecificityInterpretable Anomaly Detection in Cellular Networks by Learning Concepts in Variational Autoencoders
This paper addresses the challenges of detecting anomalies in cellular networks in an interpretable way and proposes a new approach using variational autoencoders (VAEs) that learn interpretable representations of the la…
Anomaly DetectionRepresentation LearningAnalysis of Variational Sparse Autoencoders
Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporatin…