110 citations · 867 across the 51 of their papers we have counts for
14 papers · 1 filter
Topology-Imbalance Learning for Semi-Supervised Node Classification
Deli Chen, Yankai Lin, Guangxiang Zhao +4
The class imbalance problem, as an important issue in learning node representations, has drawn increasing attention from the community. Although the imbalance considered by existin…
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Guangxiang Zhao, Wenkai Yang, Xuancheng Ren +3
The conventional wisdom behind learning deep classification models is to focus on bad-classified examples and ignore well-classified examples that are far from the decision boundar…
Adversarial Parameter Defense by Multi-Step Risk Minimization
Zhiyuan Zhang, Ruixuan Luo, Xuancheng Ren +3
Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show…
Rethinking Skip Connection with Layer Normalization in Transformers and ResNets
Fenglin Liu, Xuancheng Ren, Zhiyuan Zhang +2
Skip connection, is a widely-used technique to improve the performance and the convergence of deep neural networks, which is believed to relieve the difficulty in optimization due…
Rethinking the Promotion Brought by Contrastive Learning to Semi-Supervised Node Classification
Deli Chen, Yankai Lin, Lei Li +4
Graph Contrastive Learning (GCL) has proven highly effective in promoting the performance of Semi-Supervised Node Classification (SSNC). However, existing GCL methods are generally…
Collaborative Group Learning
Shaoxiong Feng, Hongshen Chen, Xuancheng Ren +3
Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically str…
Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption
Xu Sun, Zhiyuan Zhang, Xuancheng Ren +2
We argue that the vulnerability of model parameters is of crucial value to the study of model robustness and generalization but little research has been devoted to understanding th…
An Adaptive and Momental Bound Method for Stochastic Learning
Jianbang Ding, Xuancheng Ren, Ruixuan Luo +1
Training deep neural networks requires intricate initialization and careful selection of learning rates. The emergence of stochastic gradient optimization methods that use adaptive…
Memorized Sparse Backpropagation
Zhiyuan Zhang, Pengcheng Yang, Xuancheng Ren +2
Neural network learning is usually time-consuming since backpropagation needs to compute full gradients and backpropagate them across multiple layers. Despite its success of existi…
Complex Structure Leads to Overfitting: A Structure Regularization Decoding Method for Natural Language Processing
Xu Sun, Weiwei Sun, Shuming Ma +4
Recent systems on structured prediction focus on increasing the level of structural dependencies within the model. However, our study suggests that complex structures entail high o…
Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method
Xu Sun, Xuancheng Ren, Shuming Ma +5
We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is co…
Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks
Xu Sun, Bingzhen Wei, Xuancheng Ren +1
We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method,…
Minimal Effort Back Propagation for Convolutional Neural Networks
Bingzhen Wei, Xu Sun, Xuancheng Ren +1
As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alle…
meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting
Xu Sun, Xuancheng Ren, Shuming Ma +1
We propose a simple yet effective technique for neural network learning. The forward propagation is computed as usual. In back propagation, only a small subset of the full gradient…