This work considers the category distribution heterogeneity in federated...
Nonnegative Tucker Factorization (NTF) minimizes the euclidean distance ...
An oft-cited challenge of federated learning is the presence of
heteroge...
One of the key challenges in federated learning (FL) is local data
distr...
Federated Learning (FL) under distributed concept drift is a largely
une...
Prompting has shown impressive success in enabling large pretrained lang...
In classical federated learning, the clients contribute to the overall
t...
Personalized federated learning (FL) aims to train model(s) that can per...
Video question answering is a challenging task, which requires agents to...
The federated learning (FL) framework trains a machine learning model us...
Edge computing is an emerging solution to support the future Internet of...
Nonnegative matrix factorization (NMF) based topic modeling methods do n...
Integrating Internet of Things (IoT) and edge computing for "Edge-IoT"
s...
Multichannel blind source separation aims to recover the latent sources ...
Federated learning is a distributed optimization paradigm that enables a...
In federated optimization, heterogeneity in the clients' local datasets ...
Soft Actor Critic (SAC) algorithms show remarkable performance in comple...
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous
...
Due to the massive size of the neural network models and training datase...
Distributed stochastic gradient descent (SGD) is essential for scaling t...
Federated learning (FL) is a machine learning setting where many clients...
Neural networks are known to be vulnerable to carefully crafted adversar...
Topic modeling is widely studied for the dimension reduction and analysi...
Compositional generalization is a basic mechanism in human language lear...
Distributed optimization is essential for training large models on large...
We introduce a feature scattering-based adversarial training approach fo...
Conventional adversarial training methods using attacks that manipulate ...
Object detection is an important vision task and has emerged as an
indis...
The trade-off between convergence error and communication delays in
dece...
In this paper, we study fast training of adversarially robust models. Fr...
Acquiring a large vocabulary is an important aspect of human intelligenc...
Large-scale machine learning training, in particular distributed stochas...
State-of-the-art distributed machine learning suffers from significant d...
Mobile devices supporting the "Internet of Things" (IoT), often have lim...
Fog or Edge computing has recently attracted broad attention from both
i...
The emerging Internet of Things (IoT) is facing significant scalability ...
To accelerate research on adversarial examples and robustness of machine...
Though convolutional neural networks have achieved state-of-the-art
perf...
It is very attractive to formulate vision in terms of pattern theory
Mum...
Convolutional neural networks have demonstrated their powerful ability o...
In this paper, we study the task of detecting semantic parts of an objec...
In this paper, we address the task of detecting semantic parts on partia...
It has been well demonstrated that adversarial examples, i.e., natural i...
In this paper, we study the problem of semantic part segmentation for
an...