Abstract | ||
---|---|---|
In recent years, advances in deep learning have boosted the practical development, distribution and implementation of deep neural networks (DNNs). The concept of symmetry is often adopted in a deep neural network to construct an efficient network structure tailored for a specific task, such as the classic encoder-decoder structure. Massive DNN models are diverse in category, quantity and open source frameworks for implementation. Therefore, the retrieval of DNN models has become a problem worthy of attention. To this end, we propose a new idea of generating perceptual hashes of DNN models, named HNN-Net (Hash Neural Network), to index similar DNN models by similar hash codes. The proposed HNN-Net is based on neural graph networks consisting of two stages: the graph generator and the graph hashing. In the graph generator stage, the target DNN model is first converted and optimized into a graph. Then, it is assigned with additional information extracted from the execution of the original model. In the graph hashing stage, it learns to construct a compact binary hash code. The constructed hash function can well preserve the features of both the topology structure and the semantics information of a neural network model. Experimental results demonstrate that the proposed scheme is effective to represent a neural network with a short hash code, and it is generalizable and efficient on different models. |
Year | DOI | Venue |
---|---|---|
2022 | 10.3390/sym14040810 | SYMMETRY-BASEL |
Keywords | DocType | Volume |
perceptual hash, DNN, model retrieval, graph hash, HNN-Net | Journal | 14 |
Issue | ISSN | Citations |
4 | 2073-8994 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhiying Zhu | 1 | 0 | 0.34 |
Hang Zhou | 2 | 72 | 14.04 |
Siyuan Xing | 3 | 0 | 0.34 |
Zhenxing Qian | 4 | 525 | 39.26 |
Sheng Li | 5 | 54 | 13.29 |
Xinpeng Zhang | 6 | 2541 | 174.68 |