Related papers: MO-SAE:Multi-Objective Stacked Autoencoders Optimi…
Anomaly detection significantly enhances the robustness of cloud systems. While neural network-based methods have recently demonstrated strong advantages, they encounter practical challenges in cloud environments: the contradiction between…
This paper presents an innovative movable antenna (MA)-enhanced multi-user multiple-input multiple-output (MIMO) downlink system. We aim to maximize the energy efficiency (EE) under statistical channel state information (S-CSI) through a…
Sparse autoencoders (SAEs) have been widely used for interpretability of neural networks, but their learned features often vary across seeds and hyperparameter settings. We introduce Ordered Sparse Autoencoders (OSAE), which extend…
Autoencoders have been widely used for dimensional reduction and feature extraction. Various types of autoencoders have been proposed by introducing regularization terms. Most of these regularizations improve representation learning by…
Vision Transformer (ViT) suffers from data scarcity in semi-supervised learning (SSL). To alleviate this issue, inspired by masked autoencoder (MAE), which is a data-efficient self-supervised learner, we propose Semi-MAE, a pure ViT-based…
Quantum-inspired tensor networks algorithms have shown to be effective and efficient models for machine learning tasks, including anomaly detection. Here, we propose a highly parallelizable quantum-inspired approach which we call SMT-AD…
This paper studies the computational offloading of video action recognition in edge computing. To achieve effective semantic information extraction and compression, following semantic communication we propose a novel spatiotemporal…
Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer…
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by…
Mobile Edge Computing (MEC) has recently emerged as a promising technology in the 5G era. It is deemed an effective paradigm to support computation-intensive and delay critical applications even at energy-constrained and computation-limited…
Today very few deep learning-based mobile augmented reality (MAR) applications are applied in mobile devices because they are significantly energy-guzzling. In this paper, we design an edge-based energy-aware MAR system that enables MAR…
Anomaly detection aims to distinguish observations that are rare and different from the majority. While most existing algorithms assume that instances are i.i.d., in many practical scenarios, links describing instance-to-instance…
We present a detailed study on Variational Autoencoders (VAEs) for anomalous jet tagging at the Large Hadron Collider. By taking in low-level jet constituents' information, and training with background QCD jets in an unsupervised manner,…
Mobile edge computing (MEC) technology can reduce user latency and energy consumption by offloading computationally intensive tasks to the edge servers. Unmanned aerial vehicles (UAVs) and non-orthogonal multiple access (NOMA) technology…
Wireless goal-oriented semantic communication (GSC) has emerged as a promising paradigm by directly optimizing task performance. However, existing GSC frameworks typically operate on entire images and rely on labeled data for classification…
In recent years, edge computing, as an important pillar for future networks, has been developed rapidly. Task offloading is a key part of edge computing that can provide computing resources for resource-constrained devices to run…
Time series anomaly detection (TSAD) has long been a hot research topic in data mining due to its various applications. Recent studies challenge the effectiveness of popular deep learning methods for TSAD, suggesting their failure in…
Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not…
Missing input sequences are common in medical imaging data, posing a challenge for deep learning models reliant on complete input data. In this work, inspired by MultiMAE [2], we develop a masked autoencoder (MAE) paradigm for multi-modal,…
Mixture-of-Experts (MoE) models are designed to enhance the efficiency of large language models (LLMs) without proportionally increasing the computational demands. However, their deployment on edge devices still faces significant challenges…