Related papers: Deep Unsupervised Learning for Generalized Assignm…

Deep Neural Networks (DNN) represent the state of the art in many tasks. However, due to their overparameterization, their generalization capabilities are in doubt and still a field under study. Consequently, DNN can overfit and assign…

Cross-user variability in Human Activity Recognition (HAR) remains a critical challenge due to differences in sensor placement, body dynamics, and behavioral patterns. Traditional methods often fail to capture biomechanical invariants that…

Image segmentation is a fundamental task in computer vision. Data annotation for training supervised methods can be labor-intensive, motivating unsupervised methods. Current approaches often rely on extracting deep features from pre-trained…

Deep learning-based diagnostic models often suffer performance drops due to distribution shifts between training (source) and test (target) domains. Collecting and labeling sufficient target domain data for model retraining represents an…

Rate-splitting multiple access (RSMA) has been proven as an effective communication scheme for 5G and beyond. However, current approaches to RSMA resource management require complicated iterative algorithms, which cannot meet the stringent…

Graph matching involves combinatorial optimization based on edge-to-edge affinity matrix, which can be generally formulated as Lawler's Quadratic Assignment Problem (QAP). This paper presents a QAP network directly learning with the…

In ultra-dense millimeter wave (mmWave) networks, mmWave signals suffer from severe path losses and are easily blocked by obstacles. Meanwhile, ultra-dense deployment causes excessive handovers, which reduces the data link reliability. To…

Deep neural networks (DNNs) achieve remarkable performance but often suffer from overfitting due to their high capacity. We introduce Momentum-Adaptive Gradient Dropout (MAGDrop), a novel regularization method that dynamically adjusts…

The performance of Federated learning (FL) is negatively affected by device differences and statistical characteristics between participating clients. To address this issue, we introduce a deep unfolding network (DUN)-based technique that…

We introduce a new problem in unsupervised domain adaptation, termed as Generalized Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target labels including unknown categories. GUDA bridges the gap between…

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. In this paper, we…

This paper advances the state of the art by proposing the first comprehensive analysis and experimental evaluation of adversarial learning attacks to wireless deep learning systems. We postulate a series of adversarial attacks, and…

Cross-user variability poses a significant challenge in sensor-based Human Activity Recognition (HAR) systems, as traditional models struggle to generalize across users due to differences in behavior, sensor placement, and data…

Collaborations among multiple organizations, such as financial institutions, medical centers, and retail markets in decentralized settings are crucial to providing improved service and performance. However, the underlying organizations may…

The Linear Assignment Problem (LAP) is a fundamental combinatorial optimization task with applications ranging from computer vision to logistics. Classical exact solvers such as the Hungarian and Jonker-Volgenant (LAPJV) algorithms…

Deep reinforcement learning (DRL) has been successfully used to design forwarding strategies for multi-hop mobile wireless networks. While such strategies can be used directly for networks with varied connectivity and dynamic conditions,…

Recently, Deep Neural Networks (DNNs) have recorded great success in handling medical and other complex classification tasks. However, as the sizes of a DNN model and the available dataset increase, the training process becomes more complex…

Deep neural networks (DNNs) are emerging as a potential solution to solve NP-hard wireless resource allocation problems. However, in the presence of intricate constraints, e.g., users' quality-of-service (QoS) constraints, guaranteeing…

Deep neural networks (DNNs) can be easily fooled by adversarial attacks during inference phase when attackers add imperceptible perturbations to original examples, i.e., adversarial examples. Many works focus on adversarial detection and…

Deep learning (DL) architectures have been successfully used in many applications including wireless systems. However, they have been shown to be susceptible to adversarial attacks. We analyze DL-based models for a regression problem in the…