Unsupervised GAD methods assume the lack of anomaly labels, i.e., whethe...
Recommender systems have become indispensable in music streaming service...
Existing studies for applying the mixup technique on graphs mainly focus...
For Industry 4.0 Revolution, cooperative autonomous mobility systems are...
This paper presents the deep learning-based recent achievements to resol...
While single-cell RNA sequencing provides an understanding of the
transc...
In this paper, we investigate Unsupervised Episode Generation methods to...
Recent works demonstrate that GNN models are vulnerable to adversarial
a...
The development of urban-air-mobility (UAM) is rapidly progressing with
...
User modeling, which learns to represent users into a low-dimensional
re...
Although Graph Neural Networks (GNNs) have been successful in node
class...
Recently, molecular relational learning, whose goal is to predict the
in...
Molecular relational learning, whose goal is to learn the interaction
be...
The long-tailed problem is a long-standing challenge in Sequential
Recom...
The density of states (DOS) is a spectral property of materials, which
p...
This paper proposes a novel quantum multi-agent actor-critic networks (Q...
This paper proposes an efficient quantum train engine (EQuaTE), a novel ...
In modern networking research, infrastructure-assisted unmanned autonomo...
Sentence summarization shortens given texts while maintaining core conte...
Recent scene graph generation (SGG) frameworks have focused on learning
...
Routine clinical visits of a patient produce not only image data, but al...
Quantum machine learning (QML) has received a lot of attention according...
It has been considered that urban air mobility (UAM), also known as
dron...
Sets have been used for modeling various types of objects (e.g., a docum...
To support rapid and accurate autonomous driving services, road environm...
This paper addresses a novel multi-agent deep reinforcement learning
(MA...
Sequential recommender systems have shown effective suggestions by captu...
Existing Graph Neural Networks (GNNs) usually assume a balanced situatio...
Over the past few years, graph representation learning (GRL) has been a
...
Hypergraphs (i.e., sets of hyperedges) naturally represent group relatio...
Despite the success of Graph Neural Networks (GNNs) on various applicati...
Inspired by the recent success of self-supervised methods applied on ima...
With the great success of deep learning in various domains, graph neural...
The goal of one-class collaborative filtering (OCCF) is to identify the
...
Networks have been widely used to represent the relations between object...
Network embedding is an influential graph mining technique for represent...
The goal of network embedding is to transform nodes in a network to a
lo...
Nodes in a multiplex network are connected by multiple types of relation...
Recently, matrix factorization-based recommendation methods have been
cr...
Many real-world tasks solved by heterogeneous network embedding methods ...
The long-tail phenomenon tells us that there are many items in the tail....