Lingcn: Structural linearized graph convolutional network for homomorphically encrypted inference

H Peng, R Ran, Y Luo, J Zhao… - Advances in …, 2023‏ - proceedings.neurips.cc
Abstract The growth of Graph Convolution Network (GCN) model sizes has revolutionized
numerous applications, surpassing human performance in areas such as personal …

Adapi: Facilitating dnn model adaptivity for efficient private inference in edge computing

T Zhou, J Zhao, Y Luo, X **e, W Wen, C Ding… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Private inference (PI) has emerged as a promising solution to execute computations on
encrypted data, safeguarding user privacy and model parameters in edge computing …

[PDF][PDF] Maxk-gnn: Towards theoretical speed limits for accelerating graph neural networks training

H Peng, X **e, K Shivdikar, MD Hasan… - arxiv preprint arxiv …, 2023‏ - wiki.kaustubh.us
In the acceleration of deep neural network training, the graphics processing unit (GPU) has
become the mainstream platform. GPUs face substantial challenges on Graph Neural …

Edge-InversionNet: Enabling efficient inference of InversionNet on edge devices

Z Wang, I Putla, W Jiang, Y Lin - Third International Meeting for …, 2023‏ - library.seg.org
Seismic full waveform inversion (FWI) is a widely used technique in geophysics for inferring
subsurface structures from seismic data. And InversionNet is one of the most successful data …

Key Information Retrieval to Classify the Unstructured Data Content of Preferential Trade Agreements

J Zhao, Z Meng, S Gordeev, Z Pan, D Song… - arxiv preprint arxiv …, 2024‏ - arxiv.org
With the rapid proliferation of textual data, predicting long texts has emerged as a significant
challenge in the domain of natural language processing. Traditional text prediction methods …