32 citations · 78 across the 9 of their papers we have counts for
4 papers · 1 filter
Localised Adaptive Spatial-Temporal Graph Neural Network
Wenying Duan, Xiaoxi He, Zimu Zhou +2
Spatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what exten…
p-Meta: Towards On-device Deep Model Adaptation
Zhongnan Qu, Zimu Zhou, Yongxin Tong +1
Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data sample…
AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
Sicong Liu, Junzhao Du, Kaiming Nan +3
Recent breakthroughs in Deep Neural Networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of de…
Pruning-Aware Merging for Efficient Multitask Inference
Xiaoxi He, Dawei Gao, Zimu Zhou +2
Many mobile applications demand selective execution of multiple correlated deep learning inference tasks on resource-constrained platforms. Given a set of deep neural networks, eac…