Many real-world optimization problems possess dynamic characteristics.
E...
Cognitive diagnosis plays a vital role in modern intelligent education
p...
The problem of how to assess cross-modality medical image synthesis has ...
Optimizing building configurations for an efficient use of energy is
inc...
Popular Transformer networks have been successfully applied to remote se...
Data augmentation is a promising technique for unsupervised anomaly dete...
Reinforcement learning (RL) is a machine learning approach that trains a...
While vision transformers have been highly successful in improving the
p...
Image anomaly detection (IAD) is an emerging and vital computer vision t...
During the past decades, evolutionary computation (EC) has demonstrated
...
In the area of fewshot anomaly detection (FSAD), efficient visual featur...
The recent rapid development of deep learning has laid a milestone in
in...
Graph neural networks have received increased attention over the past ye...
Computing is a critical driving force in the development of human
civili...
The facility location problems (FLPs) are a typical class of NP-hard
com...
Data-driven evolutionary algorithms usually aim to exploit the informati...
In cooperative multi-agent reinforcement learning, centralized training ...
Multi-objective optimization problems whose objectives have different
ev...
Over recent years, there has been a rapid development of deep learning (...
The ongoing advancements in network architecture design have led to
rema...
Recent years have seen the rapid development of fairness-aware machine
l...
Deep neural networks have been found vulnerable to adversarial attacks, ...
Bayesian optimization has emerged at the forefront of expensive black-bo...
Neural architecture search (NAS) has become increasingly popular in the ...
Visual sensory anomaly detection (AD) is an essential problem in compute...
The existence of completely aligned and paired multi-modal neuroimaging ...
Self-supervised learning (SSL) has become a popular method for generatin...
The existence of completely aligned and paired multi-modal neuroimaging ...
Utilizing the paired multi-modal neuroimaging data has been proved to be...
Most existing multiobjetive evolutionary algorithms (MOEAs) implicitly a...
Data-driven optimization has found many successful applications in the r...
Federated learning is an emerging distributed machine learning framework...
In the past three decades, a large number of metaheuristics have been
pr...
Image clustering is a particularly challenging computer vision task, whi...
Due to limited computational cost and energy consumption, most neural ne...
Data-driven evolutionary optimization has witnessed great success in sol...
Many existing deep learning models are vulnerable to adversarial example...
Relation classification (RC) task is one of fundamental tasks of informa...
Existing work on data-driven optimization focuses on problems in static
...
Homomorphic encryption is a very useful gradient protection technique us...
Image clustering has recently attracted significant attention due to the...
Federated learning is a recently proposed distributed machine learning
p...
Multi-label classification consists in classifying an instance into two ...
The performance of a deep neural network is heavily dependent on its
arc...
Learning over massive data stored in different locations is essential in...
Federated learning is a distributed machine learning approach to privacy...
Designing a controller for autonomous vehicles capable of providing adeq...
Accurately locating the start and end time of an action in untrimmed vid...
Motivation: Identifying interaction clusters of large gene regulatory
ne...
Recently, more and more works have proposed to drive evolutionary algori...