Fast Unsupervised Deep Outlier Model Selection with Hypernetworks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Xueying, Zhao, Yue, Akoglu, Leman
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910575414476800
author Ding, Xueying
Zhao, Yue
Akoglu, Leman
author_facet Ding, Xueying
Zhao, Yue
Akoglu, Leman
contents Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. While several prior work report the sensitivity of OD models to HPs, it becomes ever so critical for the modern DOD models that exhibit a long list of HPs. We introduce HYPER for tuning DOD models, tackling two fundamental challenges: (1) validation without supervision (due to lack of labeled anomalies), and (2) efficient search of the HP/model space (due to exponential growth in the number of HPs). A key idea is to design and train a novel hypernetwork (HN) that maps HPs onto optimal weights of the main DOD model. In turn, HYPER capitalizes on a single HN that can dynamically generate weights for many DOD models (corresponding to varying HPs), which offers significant speed-up. In addition, it employs meta-learning on historical OD tasks with labels to train a proxy validation function, likewise trained with our proposed HN efficiently. Extensive experiments on 35 OD tasks show that HYPER achieves high performance against 8 baselines with significant efficiency gains.
format Preprint
id arxiv_https___arxiv_org_abs_2307_10529
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fast Unsupervised Deep Outlier Model Selection with Hypernetworks
Ding, Xueying
Zhao, Yue
Akoglu, Leman
Machine Learning
Artificial Intelligence
Outlier detection (OD) finds many applications with a rich literature of numerous techniques. Deep neural network based OD (DOD) has seen a recent surge of attention thanks to the many advances in deep learning. In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. While several prior work report the sensitivity of OD models to HPs, it becomes ever so critical for the modern DOD models that exhibit a long list of HPs. We introduce HYPER for tuning DOD models, tackling two fundamental challenges: (1) validation without supervision (due to lack of labeled anomalies), and (2) efficient search of the HP/model space (due to exponential growth in the number of HPs). A key idea is to design and train a novel hypernetwork (HN) that maps HPs onto optimal weights of the main DOD model. In turn, HYPER capitalizes on a single HN that can dynamically generate weights for many DOD models (corresponding to varying HPs), which offers significant speed-up. In addition, it employs meta-learning on historical OD tasks with labels to train a proxy validation function, likewise trained with our proposed HN efficiently. Extensive experiments on 35 OD tasks show that HYPER achieves high performance against 8 baselines with significant efficiency gains.
title Fast Unsupervised Deep Outlier Model Selection with Hypernetworks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2307.10529