http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114021473-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_7fd831b030989c3a5c9f7a657d2991fc |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-245 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-25 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-27 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
filingDate | 2021-11-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_abe07c967c2c5ce2c530b76b060e02b3 |
publicationDate | 2022-02-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114021473-A |
titleOfInvention | Training method, device, electronic device and storage medium for machine learning model |
abstract | The present application provides a method and device for training a machine learning model; the method includes: training a machine learning model of the training device based on a shared sample set and a private sample set of the training device to obtain a trained machine learning model; Based on the shared sample set, the trained machine learning model is called for prediction processing, and a set of predicted values is obtained; the set of predicted values is sent to the server device, and the set of predicted values is used by the server device in combination with the predicted value sets sent by other trainer devices. Fusion processing to obtain a fusion value set; receiving the fusion value set sent by the server device, and updating the shared sample set according to the fusion value set; the updated shared sample set and private sample set are used by the training device for the machine learning model. next round of training. Through this application, multi-party sample data can be fully utilized to reduce model training time and improve model training efficiency. |
priorityDate | 2021-11-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID11178 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID454006091 |
Total number of triples: 19.