Supervised learning, especially supervised deep learning, requires large...
This paper investigates methods for improving generative data augmentati...
The aggregation of multiple opinions plays a crucial role in decision-ma...
Crowdsourcing has been widely used to efficiently obtain labeled dataset...
Crowdsourcing has been used to collect data at scale in numerous fields....
Factorization machines (FMs) are a powerful tool for regression and
clas...
Offline reinforcement learning (RL) have received rising interest due to...
Human computation is an approach to solving problems that prove difficul...
The research process includes many decisions, e.g., how to entitle and w...
Finding the features relevant to the difference in treatment effects is
...
Transfer learning is crucial in training deep neural networks on new tar...
Intelligent Tutoring Systems have become critically important in future
...
A shortcoming of batch reinforcement learning is its requirement for rew...
Understanding the reasons behind the predictions made by deep neural net...
Multi-relational graph is a ubiquitous and important data structure, all...
The word mover's distance (WMD) is a fundamental technique for measuring...
Sequences of events including infectious disease outbreaks, social netwo...
The problem of estimating the probability distribution of labels has bee...
Crowd movement guidance has been a fascinating problem in various fields...
Choosing a publication venue for an academic paper is a crucial step in ...
Outcome estimation of treatments for target individuals is an important
...
The ability to predict the chemical properties of compounds is crucial i...
Given a set of ideas collected from crowds with regard to an open-ended
...
Predicting which action (treatment) will lead to a better outcome is a
c...
This study examines the time complexities of the unbalanced optimal tran...
Individual treatment effect (ITE) represents the expected improvement in...
Graph neural networks (GNNs) are powerful machine learning models for va...
The problem of comparing distributions endowed with their own geometry
a...
In this paper, from a theoretical perspective, we study how powerful gra...
Finding an optimal parameter of a black-box function is important for
se...
Finding hard instances, which need a long time to solve, of graph proble...
This paper investigates the theory of robustness against adversarial att...
Recent advancements in graph neural networks (GNN) have led to
state-of-...
Knowledge tracing is a sequence prediction problem where the goal is to
...
Graphs are general and powerful data representations which can model com...
Recent advances in graph convolutional networks have significantly impro...
Item cold-start is a classical issue in recommender systems that affects...
We study the K-armed dueling bandit problem, a variation of the standard...
Most conventional Reinforcement Learning (RL) algorithms aim to optimize...
In this paper, we propose three approaches for the estimation of the Tuc...