# Fast Unsupervised Deep Outlier Model Selection with Hypernetworks

arXiv: https://arxiv.org/abs/2307.10529 · HTML: https://mlsanity.com/paper/2307.10529/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization](https://mlsanity.com/paper/1603.06560/) (2016)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://mlsanity.com/paper/1708.05344/) (2017)
- [Graph HyperNetworks for Neural Architecture Search](https://mlsanity.com/paper/1810.05749/) (2018)
- [Predicting trends in the quality of state-of-the-art neural networks without access to training or testing data](https://mlsanity.com/paper/2002.06716/) (2020)
- [Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions](https://mlsanity.com/paper/1903.03088/) (2019)
- [Parameter Prediction for Unseen Deep Architectures](https://mlsanity.com/paper/2110.13100/) (2021)
- [Unsupervised Model Selection for Variational Disentangled Representation Learning](https://mlsanity.com/paper/1905.12614/) (2019)
- [TODS: An Automated Time Series Outlier Detection System](https://mlsanity.com/paper/2009.09822/) (2020)
- [How to Evaluate the Quality of Unsupervised Anomaly Detection Algorithms?](https://mlsanity.com/paper/1607.01152/) (2016)
- [Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution](https://mlsanity.com/paper/2206.07647/) (2022)
- [PyODDS: An End-to-end Outlier Detection System with Automated Machine Learning](https://mlsanity.com/paper/2003.05602/) (2020)
- [Toward Unsupervised Outlier Model Selection](https://mlsanity.com/paper/2211.01834/) (2022)
- [HyperMAML: Few-Shot Adaptation of Deep Models with Hypernetworks](https://mlsanity.com/paper/2205.15745/) (2022)

## Built on by (most cited first, 6 of 6)

- [MetaOOD: Automatic Selection of OOD Detection Models](https://mlsanity.com/paper/2410.03074/) (2024)
- [ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models](https://mlsanity.com/paper/2502.11059/) (2025)
- [From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection](https://mlsanity.com/paper/2602.03018/) (2026)
- [On the Detection of Reviewer-Author Collusion Rings From Paper Bidding](https://mlsanity.com/paper/2402.07860/) (2024)
- [MacrOData: New Benchmarks of Thousands of Datasets for Tabular Outlier Detection](https://mlsanity.com/paper/2602.09329/) (2026)
- [End-To-End Self-Tuning Self-Supervised Time Series Anomaly Detection](https://mlsanity.com/paper/2404.02865/) (2024)

## Abstract (arXiv)

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.