most citedUnderstanding and Utilizing Deep Neural Networks Trained with Noisy Labels

96 citations · 225 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG201965 cited

Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models

Guangyong Chen, Pengfei Chen, Chang-Yu Hsieh +9

We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science. As of June 20th 2019, the dataset comprises of…

cs.LG20195 cited

A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR

Pengfei Chen, Benben Liao, Guangyong Chen +1

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) since DNNs can easily overfit to the noisy labels. Mos…

cs.LG201917 cited

Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization

Pengfei Chen, Weiwen Liu, Chang-Yu Hsieh +2

Graph Neural Networks (GNNs) achieve an impressive performance on structured graphs by recursively updating the representation vector of each node based on its neighbors, during wh…

cs.LG20193 cited

Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction

Hongyao Tang, Jianye Hao, Guangyong Chen +4

Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochastic…

cs.LG201939 cited

Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks

Guangyong Chen, Pengfei Chen, Yujun Shi +3

In this work, we propose a novel technique to boost training efficiency of a neural network. Our work is based on an excellent idea that whitening the inputs of neural networks can…

cs.LG201996 cited

Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels

Pengfei Chen, Benben Liao, Guangyong Chen +1

Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the…