Large-scale well-annotated datasets are of great importance for training...
Semi-supervised learning (SSL) methods assume that labeled data, unlabel...
Trajectory prediction has been a crucial task in building a reliable
aut...
Data augmentation is an effective regularization strategy for mitigating...
Attaining the equilibrium state of a catalyst-adsorbate system is key to...
Uncertainty estimation is a key factor that makes deep learning reliable...
In subcellular biological research, fluorescence staining is a key techn...
Session-based recommendation (SBR) systems aim to utilize the user's
sho...
Graph neural networks (GNNs) have drawn more and more attention from mat...
Artificial intelligence has deeply revolutionized the field of medicinal...
Surgical scene segmentation is fundamentally crucial for prompting cogni...
Sign language recognition and translation first uses a recognition modul...
Due to the difficulty of collecting exhaustive multi-label annotations,
...
Precise congestion prediction from a placement solution plays a crucial ...
The backpropagation networks are notably susceptible to catastrophic
for...
Fairness in recommendation has attracted increasing attention due to bia...
Supervised learning under label noise has seen numerous advances recentl...
For multi-class classification under class-conditional label noise, we p...
Recently, many deep neural networks were designed to process 3D point cl...
Recently, deep multiagent reinforcement learning (MARL) has become a hig...
In many real-world settings, a team of cooperative agents must learn to
...
The item cold-start problem seriously limits the recommendation performa...
Collaborative filtering, a widely-used recommendation technique, predict...
Graph convolutional networks(GCNs) have become the most popular approach...
We introduce a new molecular dataset, named Alchemy, for developing mach...
Noisy labels are ubiquitous in real-world datasets, which poses a challe...
Graph Neural Networks (GNNs) achieve an impressive performance on struct...
The vulnerability to slight input perturbations is a worrying yet intrig...
Value functions are crucial for model-free Reinforcement Learning (RL) t...
In this work, we propose a novel technique to boost training efficiency ...
Noisy labels are ubiquitous in real-world datasets, which poses a challe...
Dyadic Data Prediction (DDP) is an important problem in many research ar...
Most existing image denoising approaches assumed the noise to be homogen...