相关论文: Deep Learning Autoencoders for Reducing PAPR in Co…

This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (Deep Autoencoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network in a non-iterative way,…

Modulation constellation design is a core challenge in digital communications, especially under stringent demands on spectral efficiency, robustness, and energy consumption. Classical schemes like PSK and QAM, while analytically tractable,…

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Anomalies (or outliers) are prevalent in real-world empirical observations and potentially mask important underlying structures. Accurate identification of anomalous samples is crucial for the success of downstream data analysis tasks. To…

Active learning has been studied extensively as a method for efficient data collection. Among the many approaches in literature, Expected Error Reduction (EER) (Roy and McCallum) has been shown to be an effective method for active learning:…

We consider the peak-to-average power ratio (PAPR) reduction challenge of orthogonal frequency division multiplexing (OFDM) systems utilizing tone reservation (TR) under a sensing-enabling constraint, such that the signals placed in the…

Audio Adversarial Examples (AAE) represent specially created inputs meant to trick Automatic Speech Recognition (ASR) systems into misclassification. The present work proposes MP3 compression as a means to decrease the impact of Adversarial…

Deep learning, as widely known, is vulnerable to adversarial samples. This paper focuses on the adversarial attack on autoencoders. Safety of the autoencoders (AEs) is important because they are widely used as a compression scheme for data…

Unsupervised learning is becoming more and more important recently. As one of its key components, the autoencoder (AE) aims to learn a latent feature representation of data which is more robust and discriminative. However, most AE based…

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by…

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Ensembling deep learning models is a shortcut to promote its implementation in new scenarios, which can avoid tuning neural networks, losses and training algorithms from scratch. However, it is difficult to collect sufficient accurate and…

We present an extension to masked autoencoders (MAE) which improves on the representations learnt by the model by explicitly encouraging the learning of higher scene-level features. We do this by: (i) the introduction of a perceptual…

In order to learn universal sentence representations, previous methods focus on complex recurrent neural networks or supervised learning. In this paper, we propose a mean-max attention autoencoder (mean-max AAE) within the encoder-decoder…

The electrocardiogram (ECG) is an inexpensive and widely available tool for cardiovascular assessment. Despite its standardized format and small file size, the high complexity and inter-individual variability of ECG signals (typically a…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single…

This paper focuses on the performance analysis of a class of limited peak-to-average power ratio (PAPR) precoders for downlink multi-user massive multiple-input multiple-output (MIMO) systems. Contrary to conventional precoding approaches…

Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets. In this work, we ask whether it is possible to achieve similar results…

Modern LLMs face inference efficiency challenges due to their scale. To address this, many compression methods have been proposed, such as pruning and quantization. However, the effect of compression on a model's interpretability remains…