相关论文: Combining Resonant and Tail-based Anomaly Detectio…

Most sparticle decay cascades envisaged at the Large Hadron Collider (LHC) involve hadronic decays of intermediate particles. We use state-of-the art techniques based on the \kt jet algorithm to reconstruct the resulting hadronic final…

We propose a Hybrid classical-quantum Autoencoder (HAE) model, which is a synergy of a classical autoencoder (AE) and a parametrized quantum circuit (PQC) that is inserted into its bottleneck. The PQC augments the latent space, on which a…

In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to…

Hadronic resonances are crucial probes to understand the various phases of matter created during relativistic heavy-ion collisions. Due to their short lifetimes, the yields of these resonances can be affected by competing rescattering and…

We conduct systematic studies of the optical characteristics of plasmonic nanoparticles that exhibit C2v symmetry. We analyze three distinct geometric configurations: an L-type shape, a crescent, and a split-ring resonator. Optical…

Performing anomaly detection in hybrid systems is a challenging task since it requires analysis of timing behavior and mutual dependencies of both discrete and continuous signals. Typically, it requires modeling system behavior, which is…

We present a model for tail wavelets, a phenomenon also known as "echo" in the literature. The tail wavelet may appear in signal reconnaissances in the merger of binary compact objects, including black holes and neutron stars. We show that…

Real-world data is often unbalanced and long-tailed, but deep models struggle to recognize rare classes in the presence of frequent classes. To address unbalanced data, most studies try balancing the data, the loss, or the classifier to…

Anomaly detection is crucial in industrial applications for identifying rare and unseen patterns to ensure system reliability. Traditional models, trained on a single class of normal data, struggle with real-world distributions where normal…

Graph anomaly detection (GAD) aims to identify nodes that deviate from normal patterns in structure or features. While recent GNN-based approaches have advanced this task, they struggle with two major challenges: 1) homophily disparity,…

Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonomous driving, for instance, a steering command might be internally consistent but decouple from the…

Real-world data tends to follow a long-tailed distribution, where the class imbalance results in dominance of the head classes during training. In this paper, we propose a frustratingly simple but effective step-wise learning framework to…

We study the LHC signal of a light gluino whose cascade decay is dominated by channels involving top, and, sometimes, bottom quarks. This is a generic signature for a number of supersymmetry breaking scenarios considered recently, where the…

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved…

Identifying anomalous instances in tabular data is essential for improving data reliability and maintaining system stability. Due to the scarcity of ground-truth anomaly labels, existing methods mainly rely on unsupervised anomaly detection…

Lattice growth models where uncorrelated random deposition competes with some aggregation dynamics that generates correlations are studied with rates of the correlated component decreasing as a power law. These models have anomalous…

Detecting anomalies in the data collected by WSNs can provide crucial evidence for assessing the reliability and stability of WSNs. Existing methods for WSN anomaly detection often face challenges such as the limited extraction of…

Two analyses searching for the production of supersymmetric particles through the electroweak interaction are presented: the chargino search, targeting the pair production of charginos decaying into W bosons and neutralinos, and the…

In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to…

An attempt is made to present the effect of new physics in the exclusive decays of W boson at high energy colliders in the Randall-Sundrum (RS) model. By using Feynman diagram techniques we have evaluated the influence of the scalar…