Study on Data Filling Based on Global-attributes Attention Neural Process Model
The attention neural process(ANP) model which adopts the method of generative model,takes any number context points of the sample as input,and outputs the distribution function of the entire sample,so as to approximate the function of Gaussian process regression(GPR) to realize the data fullfilling...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial office of Computer Science
2022-10-01
|
| Series: | Jisuanji kexue |
| Subjects: | |
| Online Access: | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-10-111.pdf |
| _version_ | 1797845156192321536 |
|---|---|
| author | CHEN Kai, LIU Man, WANG Zhi-teng, MAO Shao-chen, SHEN Qiu-hui, ZHANG Hong-jun |
| author_facet | CHEN Kai, LIU Man, WANG Zhi-teng, MAO Shao-chen, SHEN Qiu-hui, ZHANG Hong-jun |
| author_sort | CHEN Kai, LIU Man, WANG Zhi-teng, MAO Shao-chen, SHEN Qiu-hui, ZHANG Hong-jun |
| collection | DOAJ |
| description | The attention neural process(ANP) model which adopts the method of generative model,takes any number context points of the sample as input,and outputs the distribution function of the entire sample,so as to approximate the function of Gaussian process regression(GPR) to realize the data fullfilling task.In reality,many scenes or datasets containe the attributes or labels data which are critical for generating the missing data.However,the ANP ignores full use of them.Inspired by CVAE model which control sample generation with lable as condition,this paper proposes global attribute attentional neural process(GANP),which embeds sample attributes or labels into ANP network to make the model generate samples more accurately,especially when the number of input context points are scarce.In detail,the sample attributes are embedded into the encoder network,so that the latent variables contain the sample attribute information.At the same time,the sample attributes are added as features in the decoder network to help generate more accurate samples.Finally,experimental results prove the superiority of GANP in both qualitative and quantitative,and it also reveals that GANP expands the application of NP families which can solve the Gaus-sian process regression problem more flexibly,quickly and accurately. |
| first_indexed | 2024-04-09T17:34:00Z |
| format | Article |
| id | doaj.art-c466e55ee90e499b83001c100f179f68 |
| institution | Directory Open Access Journal |
| issn | 1002-137X |
| language | zho |
| last_indexed | 2024-04-09T17:34:00Z |
| publishDate | 2022-10-01 |
| publisher | Editorial office of Computer Science |
| record_format | Article |
| series | Jisuanji kexue |
| spelling | doaj.art-c466e55ee90e499b83001c100f179f682023-04-18T02:32:39ZzhoEditorial office of Computer ScienceJisuanji kexue1002-137X2022-10-01491011111710.11896/jsjkx.210800038Study on Data Filling Based on Global-attributes Attention Neural Process ModelCHEN Kai, LIU Man, WANG Zhi-teng, MAO Shao-chen, SHEN Qiu-hui, ZHANG Hong-jun01 Institute of Command and Control Engineering,Army Engineering University of PLA,Nanjing 210007,China ;2 73131 Unit of PLA,Zhangzhou,Fujian 363000,ChinaThe attention neural process(ANP) model which adopts the method of generative model,takes any number context points of the sample as input,and outputs the distribution function of the entire sample,so as to approximate the function of Gaussian process regression(GPR) to realize the data fullfilling task.In reality,many scenes or datasets containe the attributes or labels data which are critical for generating the missing data.However,the ANP ignores full use of them.Inspired by CVAE model which control sample generation with lable as condition,this paper proposes global attribute attentional neural process(GANP),which embeds sample attributes or labels into ANP network to make the model generate samples more accurately,especially when the number of input context points are scarce.In detail,the sample attributes are embedded into the encoder network,so that the latent variables contain the sample attribute information.At the same time,the sample attributes are added as features in the decoder network to help generate more accurate samples.Finally,experimental results prove the superiority of GANP in both qualitative and quantitative,and it also reveals that GANP expands the application of NP families which can solve the Gaus-sian process regression problem more flexibly,quickly and accurately.https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-10-111.pdfneural process|cross attention|variational inference|gaussian process|global attribute |
| spellingShingle | CHEN Kai, LIU Man, WANG Zhi-teng, MAO Shao-chen, SHEN Qiu-hui, ZHANG Hong-jun Study on Data Filling Based on Global-attributes Attention Neural Process Model Jisuanji kexue neural process|cross attention|variational inference|gaussian process|global attribute |
| title | Study on Data Filling Based on Global-attributes Attention Neural Process Model |
| title_full | Study on Data Filling Based on Global-attributes Attention Neural Process Model |
| title_fullStr | Study on Data Filling Based on Global-attributes Attention Neural Process Model |
| title_full_unstemmed | Study on Data Filling Based on Global-attributes Attention Neural Process Model |
| title_short | Study on Data Filling Based on Global-attributes Attention Neural Process Model |
| title_sort | study on data filling based on global attributes attention neural process model |
| topic | neural process|cross attention|variational inference|gaussian process|global attribute |
| url | https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-10-111.pdf |
| work_keys_str_mv | AT chenkailiumanwangzhitengmaoshaochenshenqiuhuizhanghongjun studyondatafillingbasedonglobalattributesattentionneuralprocessmodel |