Related papers: Meta-Learning for Unsupervised Outlier Detection w…

We study a novel machine learning (ML) problem setting of sequentially allocating small subsets of training data amongst a large set of classifiers. The goal is to select a classifier that will give near-optimal accuracy when trained on all…

While machine learning and artificial intelligence have long been applied in networking research, the bulk of such works has focused on supervised learning. Recently there has been a rising trend of employing unsupervised machine learning…

This paper develops a flexible distribution-free method for collective outlier detection and enumeration, designed for situations in which the presence of outliers can be detected powerfully even though their precise identification may be…

Meta-learning, or "learning to learn," is a subfield of machine learning where the goal is to develop models and algorithms that can learn from various tasks and improve their learning process over time. Unlike traditional machine learning…

Out-of-distribution (OOD) detection aims to identify test examples that do not belong to the training distribution and are thus unlikely to be predicted reliably. Despite a plethora of existing works, most of them focused only on the…

We develop techniques to quantify the degree to which a given (training or testing) example is an outlier in the underlying distribution. We evaluate five methods to score examples in a dataset by how well-represented the examples are, for…

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning…

Semantically coherent out-of-distribution (SCOOD) detection aims to discern outliers from the intended data distribution with access to unlabeled extra set. The coexistence of in-distribution and out-of-distribution samples will exacerbate…

Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation…

The accuracy of machine learning interatomic potentials suffers from reference data that contains numerical noise. Often originating from unconverged or inconsistent electronic-structure calculations, this noise is challenging to identify.…

Anomaly detection has many applications ranging from bank-fraud detection and cyber-threat detection to equipment maintenance and health monitoring. However, choosing a suitable algorithm for a given application remains a challenging design…

Categorization is one of the basic tasks in machine learning and data analysis. Building on formal concept analysis (FCA), the starting point of the present work is that different ways to categorize a given set of objects exist, which…

Out-of-distribution recognition forms an important and well-studied problem in deep learning, with the goal to filter out samples that do not belong to the distribution on which a network has been trained. The conclusion of this paper is…

Anomaly detection (AD), separating anomalies from normal data, has many applications across domains, from security to healthcare. While most previous works were shown to be effective for cases with fully or partially labeled data, that…

Autoencoders, as a dimensionality reduction technique, have been recently applied to outlier detection. However, neural networks are known to be vulnerable to overfitting, and therefore have limited potential in the unsupervised outlier…

Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…

In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in…

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image…

Many methods have been proposed to detect concept drift, i.e., the change in the distribution of streaming data, due to concept drift causes a decrease in the prediction accuracy of algorithms. However, the most of current detection methods…