From the 1 of 1.9k papers with an AI index.
1k citations
- Peking UniversityCN608 papers
- Tsinghua UniversityCN476 papers
- Carnegie Mellon UniversityUS417 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT405 papers
- University of Science and Technology of ChinaCN405 papers
- University of Chinese Academy of SciencesCN377 papers
- Institute of Modern PhysicsCN374 papers
- Institute of High Energy PhysicsCN362 papers
- Zhejiang UniversityCN362 papers
- University of TurinIT361 papers
- University of PerugiaIT356 papers
- Università degli Studi del Piemonte Orientale “Amedeo Avogadro”IT351 papers
11 papers · 2 filters
Towards Unified INT8 Training for Convolutional Neural Network
Feng Zhu, Ruihao Gong, Fengwei Yu +5
Recently low-bit (e.g., 8-bit) network quantization has been extensively studied to accelerate the inference. Besides inference, low-bit training with quantized gradients can furth…
Graph Markov Network for Traffic Forecasting with Missing Data
Zhiyong Cui, Longfei Lin, Ziyuan Pu +1
Traffic forecasting is a classical task for traffic management and it plays an important role in intelligent transportation systems. However, since traffic data are mostly collecte…
Structure of Deep Neural Networks with a Priori Information in Wireless Tasks
Jia Guo, Chenyang Yang
Deep neural networks (DNNs) have been employed for designing wireless networks in many aspects, such as transceiver optimization, resource allocation, and information prediction. E…
Regularized Non-negative Spectral Embedding for Clustering
Yifei Wang, Rui Liu, Yong Chen +2
Spectral Clustering is a popular technique to split data points into groups, especially for complex datasets. The algorithms in the Spectral Clustering family typically consist of…
Mobile APP User Attribute Prediction by Heterogeneous Information Network Modeling
Hekai Zhang, Jibing Gong, Zhiyong Teng +4
User-based attribute information, such as age and gender, is usually considered as user privacy information. It is difficult for enterprises to obtain user-based privacy attribute…
MixUp as Directional Adversarial Training
Guillaume P. Archambault, Yongyi Mao, Hongyu Guo +1
In this work, we explain the working mechanism of MixUp in terms of adversarial training. We introduce a new class of adversarial training schemes, which we refer to as directional…