Transfer learning for performance prediction
AssigneeTelefonaktiebolaget LM Ericsson (publ)
InventorsJalil TAGHIA, Isak PERSSON, Xiaoyu LAN, Masoumeh EBRAHIMI
Life of this patent
Estimating the term…
Abstract
A method, system and apparatus are disclosed. A method implemented in a source network node configured to communicate with a target network node is provided. A source data set is obtained. A source model is trained based on the source dataset, where the training includes generating a source memory matrix and a source link matrix. The source memory matrix and the source link matrix are transmitted to the target network node, which causes the target network node to train a target model. The training of the target model includes initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.
Claims24
A source network node configured to communicate with a target network node, the source network node one or more of configured to, comprising a radio interface and comprising processing circuitry configured to:
- one or more of generate, obtain, and receive a source dataset;
- train a source model based on the source dataset, the training including generating a source memory matrix and a source link matrix;
- and
- cause a transmission of the source memory matrix and the source link matrix to the target network node, the transmission being configured to cause the target network node to train a target model, the training of the target model including initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.
(canceled)
A method implemented in a source network node configured to communicate with a target network node, the method comprising:
- one or more of generating, obtaining, and receiving a source dataset;
- training a source model based on the source dataset, the training including generating a source memory matrix and a source link matrix;
- and
- causing a transmission of the source memory matrix and the source link matrix to the target network node, the transmission being configured to cause the target network node to train a target model, the training of the target model including initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.
-14. (canceled)
A target network node configured to communicate with a source network node, the target network node one or more of configured to, comprising a radio interface and comprising processing circuitry configured to:
- one or more of generate, obtain, and receive a target dataset;
- receive a source memory matrix and a source link matrix from the source network node, the source memory matrix and the source link matrix being associated with a source model, the source model being trained based on a source dataset;
- and
- train a target model on the target dataset, the training of the target model including initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.
(canceled)
A method implemented in a target network node configured to communicate with a source network node, the method comprising:
- one or more of generating, obtaining, and receiving a target dataset;
- receiving a source memory matrix and a source link matrix from the source network node, the source memory matrix and the source link matrix being associated with a source model, the source model being trained based on a source dataset;
- and
- training a target model on the target dataset, the training of the target model including initializing a target memory matrix and a target link matrix based on the source memory matrix and the source link matrix.
-28. (canceled)
Dependencies are inferred from the claim text.