activity
20192021
most citedUnderstanding and Utilizing Deep Neural Networks Trained with Noisy Labels

96 citations · 250 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG20211 cited

Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction

Hongyao Tang, Jianye Hao, Guangyong Chen +6

Value function is the central notion of Reinforcement Learning (RL). Value estimation, especially with function approximation, can be challenging since it involves the stochasticit…

cs.LG202014 cited

Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise

Pengfei Chen, Junjie Ye, Guangyong Chen +2

Supervised learning under label noise has seen numerous advances recently, while existing theoretical findings and empirical results broadly build up on the class-conditional noise…

cs.LG202010 cited

Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels

Pengfei Chen, Junjie Ye, Guangyong Chen +2

For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essentia…

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…