1.5k citations · 2.5k across the 34 of their papers we have counts for
7 papers · 1 filter
Asymmetric Polynomial Loss For Multi-Label Classification
Yusheng Huang, Jiexing Qi, Xinbing Wang +1
Various tasks are reformulated as multi-label classification problems, in which the binary cross-entropy (BCE) loss is frequently utilized for optimizing well-designed models. Howe…
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
Yunchong Song, Chenghu Zhou, Xinbing Wang +1
Most graph neural networks follow the message passing mechanism. However, it faces the over-smoothing problem when multiple times of message passing is applied to a graph, causing…
Ordered Memory
Yikang Shen, Shawn Tan, Arian Hosseini +3
Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty of training memory models remains a pro…
Architectural Complexity Measures of Recurrent Neural Networks
Saizheng Zhang, Yuhuai Wu, Tong Che +4
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs). Our main contribution is twofold: first, we present a rigorous graph-theo…
How far can we go without convolution: Improving fully-connected networks
Zhouhan Lin, Roland Memisevic, Kishore Konda
We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and…
Neural Networks with Few Multiplications
Zhouhan Lin, Matthieu Courbariaux, Roland Memisevic +1
For most deep learning algorithms training is notoriously time consuming. Since most of the computation in training neural networks is typically spent on floating point multiplicat…
Towards Biologically Plausible Deep Learning
Yoshua Bengio, Dong-Hyun Lee, Jorg Bornschein +2
Neuroscientists have long criticised deep learning algorithms as incompatible with current knowledge of neurobiology. We explore more biologically plausible versions of deep repres…