H
Hao Yang
Researcher at Nokia
Publications - 119
Citations - 5676
Hao Yang is an academic researcher from Nokia. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 31, co-authored 91 publications receiving 4901 citations. Previous affiliations of Hao Yang include University of California, Los Angeles & IBM.
Papers
More filters
Journal ArticleDOI
Security in mobile ad hoc networks: challenges and solutions
TL;DR: The security issues related to this problem are identified, the challenges to security design are discussed, and the state-of-the-art security proposals that protect the MANET link- and network-layer operations of delivering packets over the multihop wireless channel are reviewed.
Proceedings ArticleDOI
Robust rate adaptation for 802.11 wireless networks
TL;DR: This paper designs and implements a new Robust Rate Adaptation Algorithm (RRAA), which uses short-term loss ratio to opportunistically guide its rate change decisions, and an adaptive RTS filter to prevent collision losses from triggering rate decrease.
Proceedings ArticleDOI
Interpretable Convolutional Neural Networks with Dual Local and Global Attention for Review Rating Prediction
TL;DR: The proposed convolutional neural networks with dual attention model outperforms HFT and ConvMF+ in terms of mean square errors (MSE) and the superior quality of user/item embeddings learned from the model is compared.
Proceedings ArticleDOI
DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks
TL;DR: DySAT is a novel neural architecture that learns node representations to capture dynamic graph structural evolution and ablation study validates the effectiveness of jointly modeling structural and temporal self-attention.
Proceedings ArticleDOI
SmartSiren: virus detection and alert for smartphones
TL;DR: SmartSiren is presented, a collaborative virusdetection and alert system for smartphones that uses a proxy-based architecture to offload the processing burden from resource-constrained smartphones and simplify the collaboration among smartphones.