Reinforcement learning is an essential paradigm for solving sequential
d...
A robust summarization system should be able to capture the gist of the
...
Distribution shift (e.g., task or domain shift) in continual learning (C...
As a few large-scale pre-trained models become the major choices of vari...
Graph neural networks (GNNs) have shown their superiority in modeling gr...
Unsupervised anomaly detection (AD) is a challenging task in realistic
a...
In a federated learning system, the clients, e.g. mobile devices and
org...
Deep reinforcement learning provides a promising approach for text-based...
Open banking enables individual customers to own their banking data, whi...
Healthcare representation learning on the Electronic Health Record (EHR)...
Graph convolutional networks are becoming indispensable for deep learnin...
Zero-shot learning (ZSL) aims to classify images of an unseen class only...
Multi-graph multi-label learning (Mgml) is a supervised learning
framewo...
Numerous deep reinforcement learning agents have been proposed, and each...
We study reinforcement learning (RL) for text-based games, which are
int...
Many graph embedding approaches have been proposed for knowledge graph
c...
The goal of zero-shot learning (ZSL) is to train a model to classify sam...
Electronic health records (EHRs) are longitudinal records of a patient's...
We study many-class few-shot (MCFS) problem in both supervised learning ...
Modeling multivariate time series has long been a subject that has attra...
Meta-learning extracts the common knowledge acquired from learning diffe...
Graph clustering is a fundamental task which discovers communities or gr...
Spatial-temporal graph modeling is an important task to analyze the spat...
A variety of machine learning applications expect to achieve rapid learn...
Traditional network embedding primarily focuses on learning a dense vect...
Network embedding aims to learn a latent, low-dimensional vector
represe...
Graph embedding aims to transfer a graph into vectors to facilitate
subs...
Deep learning has revolutionized many machine learning tasks in recent y...
Data similarity (or distance) computation is a fundamental research topi...
In this paper, we propose a self-attention mechanism, dubbed "fast
direc...
Recurrent neural networks (RNN), convolutional neural networks (CNN) and...
Graph embedding is an effective method to represent graph data in a low
...
Many natural language processing tasks solely rely on sparse dependencie...
There is an emerging trend to leverage noisy image datasets in many visu...
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are wide...
In this paper, we focus on automatically detecting events in unconstrain...