Technology
Fine-grained Optimization of Deep Neural Networks
Neural Information Processing Systems http://nips.cc/
FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations
Our method, F i GUR e, achieves an average gain of up to 4.4%, compared to the
Metric Learning for Adversarial Robustness
Chengzhi Mao, Ziyuan Zhong, Junfeng Yang, Carl Vondrick, Baishakhi Ray
Deep networks achieve impressive accuracy and wide adoption in computer vision [17], speech recognition [14], and natural language processing [21].
c24cd76e1ce41366a4bbe8a49b02a028-AuthorFeedback.pdf
We thank the reviewers [R1, R2, R3] for their valuable and constructive comments. We are glad that all of them1 appreciate the novelty of the proposed metric learning approach for adversarial robustness.
On Neuronal Capacity
Neural Information Processing Systems http://nips.cc/
Adaptive GNN for Image Analysis and Editing
Lingyu Liang, LianWen Jin, Yong Xu
Neural Information Processing Systems http://nips.cc/
Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices
If the required memory to train a model exceeds this limit, the device will be excluded from the training.
Unified Language Model Pre-training for Natural Language Understanding and Generation
Li Dong, Nan Yang, Wenhui Wang, Furu Wei, Xiaodong Liu, Yu Wang, Jianfeng Gao, Ming Zhou, Hsiao-Wuen Hon
This paper presents anewUNIfied pre-trainedLanguageModel (UNILM)that can be fine-tuned for both natural language understanding and generation tasks.